MEPS HC-020: 1997 Full Year Consolidated Data File
May 2001
Agency for Healthcare Research and Quality
Center for Cost and Financing Studies
2101 East Jefferson Street, Suite 501
Rockville, MD 20852
(301) 594-1406
TABLE OF CONTENTS
A. Data Use Agreement
B. Background
1.0 Household Component
2.0 Medical Provider Component
3.0 Insurance Component
4.0 Nursing Home Component
5.0 Survey Management
C. Technical and Programming Information
1.0 General Information
2.0 Data File Information
2.1 Codebook Structure
2.2 Reserved Codes
2.3 Codebook Format
2.4 Variable Naming
2.5 File Contents
2.5.1 Survey Administration Variables
2.5.2 Navigating the MEPS Data with Information on Person
Disposition Status
2.5.3 Geographic Variables
2.5.4 Demographic Variables
2.5.5 Income and Tax Filing Variables
2.5.5.1 Income Top-Coding
2.5.5.2 Poverty Status
2.5.6 Employment Variables
2.5.7 Health Insurance Variables
2.5.8 Health Status Variables
2.5.8.1 Perceived Health Status and ADL and IADL
Limitations
2.5.8.2 Functional and Activity Limitations
2.5.8.3 Vision Problems
2.5.8.4 Hearing Problems
2.5.8.5 Any Limitation Rounds 3, 4, and 5 (Panel 1) / Rounds
1, 2, and 3 (Panel 2)
2.5.8.6 Children’s Health Status
2.5.9 Utilization, Expenditures and Source of Payment Variables
(TOTTCH97-RXOSR97)
2.5.9.1 Expenditures Definition
2.5.9.2 Utilization and Expenditure Variables by
Type of Medical Service
3.0 Survey Sample Information
3.1 Sample Design and Response Rates
3.2 Person Level Estimation using this MEPS PUF
3.3 Family Level Estimation Using this MEPS PUF
D. Variable-Source Crosswalk
Appendix 1: Estimation Procedures in the Household Component of the 1996
Medical Expenditure Panel Survey A1-
Appendix 2: Sample Design of the 1997 Medical Expenditure Panel Survey:
Household Component A2-
Appendix 3: Summary of Utilization and Expenditure Variables by Health
Service Category A3-
A. Data Use
Agreement
Individual identifiers have been removed from the micro-data
contained in the files on this CD-ROM. Nevertheless, under sections 308 (d) and
903 (c) of the Public Health Service Act (42 U.S.C. 242m and 42 U.S.C. 299 a-1),
data collected by the Agency for Health Care Policy and Research (AHCPR) and /or
the National Center for Health Statistics (NCHS) may not be used for any purpose
other than for the purpose for which it was supplied; any effort to determine
the identity of any reported cases, is prohibited by law.
Therefore in accordance with the above referenced Federal
Statute, it is understood that:
- No one is to use the data in this data set in any way except for
statistical reporting and analysis; and
- If the identity of any person or establishment should be discovered
inadvertently, then (a) no use will be made of this knowledge, (b) The
Director Office of Management AHCPR will be advised of this incident, (c)
the information that would identify any individual or establishment will be
safeguarded or destroyed, as requested by AHCPR, and (d) no one else will be
informed of the discovered identity.
- No one will attempt to link this data set with individually identifiable
records from any data sets other than the Medical Expenditure Panel survey
or the National Health Interview Survey.
By using this data you signify your agreement to comply with
the above stated statutorily based requirements with the knowledge that
deliberately making a false statement in any matter within the jurisdiction of
any department or agency of the Federal Government violates 18 U.S.C. 1001 and
is punishable by a fine of up to $10,000 or up to 5 years in prison.
The Agency for Health Care Policy and Research requests that users cite AHCPR
and the Medical Expenditure Panel Survey as the data source in any publications
or research based upon these data. Return To Table Of Contents
B.
Background
This documentation describes one in a series of public use
files from the Medical Expenditure Panel Survey (MEPS). The survey provides a
new and extensive data set on the use of health services and health care in the United States.
The Medical Expenditure Panel Survey (MEPS) is conducted to
provide nationally representative estimates of health care use, expenditures,
sources of payment, and insurance coverage for the U.S. civilian
non-institutionalized population. MEPS also includes a nationally representative
survey of nursing homes and their residents. MEPS is cosponsored by the Agency
for Healthcare Research and Quality (AHRQ) and the National Center for Health
Statistics (NCHS).
MEPS comprises four component surveys: the Household
Component (HC), the Medical Provider Component (MPC), the Insurance Component
(IC), and the Nursing Home Component (NHC). The HC is the core survey, and it
forms the basis for the MPC sample and part of the IC sample. The separate NHC
sample supplements the other MEPS components. Together these surveys yield
comprehensive data that provide national estimates of the level and distribution
of health care use and expenditures, support health services research, and can
be used to assess health care policy implications. Return To Table Of Contents
MEPS is the third in a series of national probability surveys
conducted by AHRQ on the financing and use of medical care in the United States.
The National Medical Care Expenditure Survey (NMCES, also known as NMES-1) was
conducted in 1977, the National Medical Expenditure Survey (NMES-2) in 1987.
Beginning in 1996, MEPS continues this series with design enhancements and
efficiencies that provide a more current data resource to capture the changing
dynamics of the health care delivery and insurance system.
The design efficiencies incorporated into MEPS are in
accordance with the Department of Health and Human Services (DHHS) Survey
Integration Plan of June 1995, which focused on consolidating DHHS surveys,
achieving cost efficiencies, reducing respondent burden, and enhancing
analytical capacities. To accommodate these goals, new MEPS design features
include linkage with the National Health Interview Survey (NHIS), from which the
sampled households for the MEPS HC are drawn, and continuous longitudinal data
collection for core survey components. The MEPS HC augments NHIS by selecting a
sample of NHIS respondents, collecting additional data on their health care
expenditures, and linking these data with additional information collected from
the respondents’ medical providers, employers, and insurance providers. Return To Table Of Contents
1.0
Household Component
The MEPS HC, a nationally representative survey of the U.S.
civilian non-institutionalized population, collects medical expenditure data at
both the person and household levels. The HC collects detailed data on
demographic characteristics, health conditions, health status, use of medical
care services, charges and payments, access to care, satisfaction with care,
health insurance coverage, income, and employment.
The HC uses an overlapping panel design in which data are
collected through a preliminary contact followed by a series of five rounds of
interviews over a 2 1/2 year period. Employing computer-assisted personal
interviewing (CAPI) technology, data on medical expenditures and use for two
calendar years are collected from each household. This series of data collection
rounds is launched each year on a new sample of households to provide
overlapping panels of survey data and, when combined with other ongoing panels,
will provide continuous and current estimates of health care expenditures.
The sample of households selected for the MEPS HC is drawn
from among respondents to the NHIS, conducted by NCHS. The NHIS provides a
nationally representative sample of the U.S. civilian non-institutionalized
population, with oversampling of Hispanics and blacks. Return To Table Of Contents
2.0
Medical Provider Component
The MEPS MPC supplements and validates information on medical
care events reported in the MEPS HC by obtaining data directly from medical
providers and pharmacies identified by household respondents. The MPC sample
includes all hospitals, hospital physicians, home health agencies, and
pharmacies reported in the HC. Also included in the MPC are office-based
physicians:
- Providing care for HC respondents receiving Medicaid
- Identified through a 75 percent sample of HC households receiving care
through an HMO (health maintenance organization) or managed care plan
- Identified through a 25 percent sample of the remaining HC households
Data are collected on medical and financial characteristics
of medical and pharmacy events reported by HC respondents, including:
- Diagnoses coded according to ICD-9-CM (9th Revision, International
Classification of Diseases) and DSM-IV (Fourth Edition, Diagnostic and
Statistical Manual of Mental Disorders)
- Physician procedure codes classified by CPT-4 (Common Procedure
Terminology, Version 4)
- Inpatient stay codes classified by DRGs (diagnosis-related groups)
- Prescriptions coded by national drug code (NDC), medication names,
strength, and quantity dispensed
- Charges, payments, and the reasons for any difference between charges and
payments
The MPC is conducted through telephone interviews and mailed
survey materials. Return To Table Of Contents
3.0
Insurance Component
The MEPS IC collects data on health insurance plans obtained
through employers, unions, and other sources of private health insurance. Data
obtained in the IC include the number and types of private insurance plans
offered, benefits associated with these plans, premiums, contributions by
employers and employees, eligibility requirements, and employer characteristics.
Establishments participating in the MEPS IC are selected
through four sampling frames:
- A list of employers or other insurance providers identified by MEPS HC
respondents who report having private health insurance at the Round 1
interview.
- A Bureau of the Census list frame of private sector business
establishments.
- The Census of Governments from Bureau of the Census.
- An Internal Revenue Service list of the self-employed.
To provide an integrated picture of health insurance, data
collected from the first sampling frame (employers and insurance providers) are
linked back to data provided by the MEPS HC respondents. Data from the other
three sampling frames are collected to provide annual national and State
estimates of the supply of private health insurance available to American
workers and to evaluate policy issues pertaining to health insurance.
The MEPS IC is an annual panel survey. Data are collected
from the selected organizations through a prescreening telephone interview, a
mailed questionnaire, and a telephone followup for nonrespondents. Return To Table Of Contents
4.0
Nursing Home Component
The 1996 MEPS NHC was a survey of nursing homes and persons
residing in or admitted to nursing homes at any time during calendar year 1996.
The NHC gathered information on the demographic characteristics, residence
history, health and functional status, use of services, use of prescription
medications, and health care expenditures of nursing home residents. Nursing
home administrators and designated staff also provided information on facility
size, ownership, certification status, services provided, revenues and expenses,
and other facility characteristics. Data on the income, assets, family
relationships, and care-giving services for sampled nursing home residents were
obtained from next-of-kin or other knowledgeable persons in the community.
The 1996 MEPS NHC sample was selected using a two-stage
stratified probability design. In the first stage, facilities were selected; in
the second stage, facility residents were sampled, selecting both persons in
residence on January 1, 1996, and those admitted during the period January 1
through December 31.
The sample frame for facilities was derived from the National
Health Provider Inventory, which is updated periodically by NCHS. The MEPS NHC
data were collected in person in three rounds of data collection over a 1 2-year
period using the CAPI system. Community data were collected by telephone using
computer-assisted telephone interviewing (CATI) technology. At the end of three
rounds of data collection, the sample consists of approximately 815 responding
facilities, 3,100 residents in the facility on January 1, and 2,200 eligible
residents admitted during 1996. Return To Table Of Contents
5.0
Survey Management
MEPS data are collected under the authority of the Public
Health Service Act. They are edited and published in accordance with the
confidentiality provisions of this act and the Privacy Act. NCHS provides
consultation and technical assistance.
As soon as data collection and editing are completed, the
MEPS survey data are released to the public in staged releases of summary
reports and microdata files. Summary reports are released as printed documents
and electronic files. Microdata files are released on CD-ROM and/or as
electronic files. A catalog of all MEPS products released to date is provided on
the AHRQ web site (http://www.meps.ahrq.gov).
Printed documents and CD-ROMs are available through the AHRQ
Publications Clearinghouse. Write or call:
AHRQ Publications Clearinghouse
Attn: (publication number)
P.O. Box 8547
Silver Spring, MD 20907
800/358-9295
410/381-3150 (callers outside the United States only)
888/586-6340 (toll-free TDD service; hearing impaired only)
Be sure to specify the AHRQ number of the document or CD-ROM
you are requesting. Selected electronic files are available from the Internet on
the AHRQ home page: http://www.meps.ahrq.gov/.
Additional information on MEPS is available from the MEPS
project manager or the MEPS public use data manager at the Center for Cost and
Financing Studies, Agency for Healthcare Research and Quality, 540 Gaither Road, Rockville, MD 20850 (301/427-1406). Return To Table Of Contents
C. Technical
and Programming Information
1.0
General Information
This documentation describes the 1997 full-year consolidated
data file from the Medical Expenditure Panel Survey Household Component (MEPS
HC). Released as an ASCII file (with related SAS programming statements), this
public use file provides information collected on a nationally representative
sample of the civilian non-institutionalized population of the United States for
calendar year 1997. This file consists of MEPS survey data obtained in Rounds 3,
4, and 5 of Panel 1 and Rounds 1, 2, and 3 of Panel 2 (i.e., the rounds for the
MEPS panels covering calendar year 1997) and contains variables pertaining to
survey administration, demographics, employment, health status, health
insurance, income, and health care utilization and expenditures.
The following documentation offers a brief overview of the
types and levels of data provided, and the content and structure of the files
and the codebook. It contains the following sections:
- Data File Information
- Survey Sample Information
- Variable-Source Crosswalk (Section D)
Detailed information on sample design can be found in
Appendixes 1 and 2. Appendix 3 provides an overview of the utilization and
expenditure variables included in this file. The codebook is provided in a
separate file, H20CB.PDF. A catalog of all MEPS products released to date and a
matrix indicating the major MEPS data items on public use files that have been
released to date are available on the AHRQ home page: http://www.meps.ahrq.gov/. Return To Table Of Contents
2.0
Data File Information
This public use dataset contains variable and frequency
distributions for a total of 34,551 persons who participated in the MEPS
Household Component of the Medical Panel Expenditure Survey in 1997. This count
includes all household survey respondents who resided in eligible responding
households. The persons were part of one of the two MEPS panels that collected
data about 1997: Rounds 3, 4, and 5 of Panel 1 or Rounds 1, 2, and 3 of Panel 2.
Of these persons, 32,636 were assigned a positive person level weight. Both
weighted and unweighted frequencies are provided for each variable. In
conjunction with the weight variable (WTDPER97) provided on this file, data for
these persons can be used to make estimates for the civilian
non-institutionalized U. S. population for 1997.
The records on this file can be linked to all other 1997
MEPS-HC public use data sets by the sample person identifier (DUPERSID). Panel 1
cases (PANEL97=1) can be linked back to the 1996 MEPS-HC public use data files.
However, the user should be aware that at this time no weight is being provided
to facilitate 2 year analysis of Panel 1 data. Return To Table Of Contents
2.1
Codebook Structure
The codebook and data file sequence lists variables in the
following order:
- Unique person identifiers
- Geographic variables
- Demographic variables
- Income and Tax Filing variables
- Employment variables
- Health Insurance variables
- Health Status variables
- Utilization and Expenditure variables
- Weight and variance estimation variables
Return To Table Of Contents
2.2
Reserved Codes
The following reserved code values are used:
|
VALUE |
DEFINITION |
| -1 |
INAPPLICABLE |
Question was not asked due to skip pattern |
| -2 |
DETERMINED IN PREVIOUS ROUND |
Question was not asked in round because there was no change in
employment status or no change in current main job since previous round. |
| -7 |
REFUSED |
Question was asked and respondent refused to answer question. |
| -8 |
DK |
Question was asked and respondent did not know answer |
| -9 |
NOT ASCERTAINED |
Interviewer did not record the data |
| -10 |
HOURLY WAGE>= $43.75 |
Hourly wage was top-coded for confidentiality. |
Note: A Reserved Code of "-3" had been used in the 1996 Full Year
files to designate "No data in round"; the –3 code is no longer used
in 1997. The analyst can used the INSCOPE variable (see Section 2.5.1 Survey
Administration Variables) to determine whether or not a person would have data
in a specific round.
Return To Table Of Contents
2.3 Codebook Format
This codebook describes an ASCII data set and provides the following
programming identifiers for each variable:
|
IDENTIFIER |
DESCRIPTION |
|
Name |
Variable name (maximum of 8 characters) |
|
Description |
Variable descriptor (maximum 40 characters) |
|
Format |
Number of bytes |
|
Type |
Type of data: numeric (indicated by NUM) or character (indicated by
CHAR) |
|
Start |
Beginning column position of variable in record |
|
End |
Ending column position of variable in record |
Return To Table Of Contents
2.4 Variable Naming
In general, variable names reflect the content of the
variable, with an eight-character limitation. Edited variables end in an X, and
are so noted in the variable label. The last two characters in round-specific
variables denote the rounds of data collection, Round 3, 4, or 5 of Panel 1 and
Round 1, 2, or 3 of Panel 2. Unless otherwise noted, variables that end in 97
represent status as of December 31, 1997.
Variables contained in this delivery were derived either from
the questionnaire itself or from the CAPI. The source of each variable is
identified in the section of the documentation entitled "Appendix D.
Variable-Source Crosswalk." Sources for each variable are indicated in one
of four ways: (1) variables derived from CAPI or assigned in sampling are so
indicated; (2) variables derived from complex algorithms associated with
re-enumeration are labeled "RE Section"; (3) variables that are
collected by one or more specific questions in the instrument have those
question numbers listed in the Source column; (4) variables constructed from
multiple questions using complex algorithms are labeled "Constructed." Return To Table Of Contents
2.5
File Contents
2.5.1
Survey Administration Variables
The survey administration variables contain information
related to conducting the interview, household and family composition, and
person-level and RU-level status codes. Data for the survey administration
variables were derived from the sampling process, the CAPI programs, or were
computed based on information provided by the respondent in the re-enumeration
section of the questionnaire. Most Survey Administration variables on this file
are asked during every round of the MEPS interview. They describe data for
Rounds 3/1, 4/2, and 5/3 status as of December 31, 1997. Variable names ending
in "xy" represent variables relevant to Round "x" of Panel 1
or Round "y" of Panel 2. For example, RULETR53 is a variable relevant
to Round 5 of Panel 1 or Round 3 of Panel 2.
The December 31, 1997 variables were developed in two ways.
Those used in the construction of eligibility, inscope, and the end
reference date, were based on an exact date. The remaining variables were
constructed using data from specific rounds, if available. If data were missing
from the target round, but were available in another round, data from that other
round were used in the variable construction. If no valid data were available
during any round of data collection, an appropriate reserved code was assigned. Return To Table Of Contents
Dwelling Units, Reporting Units, and Families
The definitions of Dwelling Units (DUs) in the MEPS Household
Survey are generally consistent with the definitions employed for the National
Health Interview Survey. The dwelling unit ID (DUID) is a five-digit random ID
number assigned after the case was sampled for MEPS. The person number (PID)
uniquely identifies all persons within the dwelling unit. The variable DUPERSID
is the combination of the variables DUID and PID.
A Reporting Unit (RU) is a person or group of persons in the
sampled dwelling unit who are related by blood, marriage, adoption, foster care
or other family association. Each RU was interviewed as a single entity for
MEPS. Thus, the RU serves chiefly as a family-based "survey"
operations unit rather than an analytic unit. Members of each RU within the DU
are identified in the first three rounds by the round-specific variables
RULETR31, RULETR42 and RULETR53. End-of-year status (as of December 31, 1997) is
indicated by the RULETR97 variable. Regardless of the legal status of their
association, two persons living together as a "family" unit were
treated as a single reporting unit if they chose to be so identified. Examples
of different types of reporting units are:
1. A married daughter and her husband living with her
parents in the same dwelling unit constitute a single reporting unit.
2. A husband and wife and their unmarried daughter, age
18, who is living away from home while at college constitute two reporting
units.
3. Three unrelated persons living in the same dwelling
unit would each constitute a distinct reporting unit (a total of three
reporting units)
Unmarried college students (less than 24 years of age) who
usually live in the sampled household,
(but were living away from home and going to school at the
time of the Round 3/1 MEPS interview) were treated as a reporting unit separate
from that of their parents for the purpose of data collection. The
round-specific variables RUSIZE31, RUSIZE42, RUSIZE53 and the end-of-year status
variable RUSIZE97 indicate the number of persons in each RU, treating each
student as a single RU separate from their parents. Thus, students are not
included in the RUSIZE count of their parents RU. However, for many analytic
objectives, the student reporting units would be combined with their parents'
reporting unit, treating the combined entity as a single family. Family
identifier and size variables are described below and include students with
their parent’s reporting unit. Return To Table Of Contents
PANEL97 is a constructed variable used to specify the panel
number for the interview. PANEL97 will indicate either Panel 1 or Panel 2 for
each interview.
The round-specific variables FAMID31, FAMID42, FAMID53 and the end-of-year
status variable FAMID97 identify a family (i.e., persons related to one another
by blood, marriage, adoption, foster care, or self-identified as a single unit)
for each round and as of December 31, 1998. The FAMID variables differ from RU
only in that student reporting units are combined with their parent’s
reporting unit.
Two other family identifiers, FAMIDYR and CPSFAMID are provided on this file.
The annualized family ID letter, FAMIDYR, identifies eligible members of the
eligible annualized families within a DU. The CPSFAMID identifies eligible
members of eligible CPS-like families at 12/31/1997. CPSFAMID represents a
redefinition of MEPS families into families defined by the Current Population
Survey (CPS). Some of the distinctions between CPS and MEPS defined families are
that MEPS families include and CPS families do not include: non-married
partners, foster children, and in-laws. These persons are considered as members
of separate families for CPS-like families. The reason CPS-like families are
defined is so that a poverty status classification variable consistent with
established definitions of poverty can be assigned to the CPS-like families and
used for weight poststratification purposes. In order to identify a person’s
family affiliation users must create a unique set of FAMID variables by
concatenating the DU identifier and the FAMID variable. Instructions to create
family estimates are described in section 3.3.
The round-specific variables FAMSZE31, FAMSZE42, FAMSZE53 and
the end-of-year status variable FAMSZE97 indicate the number of persons
associated with a single family unit after students are linked to their
associated parent RUs for analytical purposes. Family-level analyses should use
the FAMSZE variables.
Note that the variables RUSIZE31, RUSIZE42, RUSIZE53,
RUSIZE97, FAMSZE31, FAMSZE42
FAMSZE53, and FAMSZE97 exclude persons who are ineligible for
data collection (i.e., those where ELGRND31^= 1, ELGRND42 ^= 1, ELGRND53 ^= 1 or
ELGRND97 ^= 1); analysts should exclude ineligible persons in a given round from
all family-level analyses for that round.
The round-specific variables RURSLT31, RURSLT42, and RURSLT53
indicate the RU response status for each round. Users should note that the
values for RURSLT31 differ from those for RURSLT42 and RURSLT53. The values for
RURSLT31 include the following:
|
-1 |
Inapplicable |
|
60 |
Complete with RU member |
|
61 |
Complete with proxy--all RU members deceased |
|
62 |
Complete with proxy--all RU members institutionalized
or deceased |
|
63 |
Complete with proxy, other |
|
80 |
Entire RU merged with other RU |
|
81 |
Entire RU deceased before 1/1/97 |
|
82 |
Entire RU is in military BEFORE 1/1/97 |
|
83 |
RU institutionalized before 1/1/97 |
|
84 |
Entire RU left U.S. before 1/1/97 |
|
85 |
RU ineligible before 1/1/97, multi-reason |
|
86 |
RU ineligible, non-key NHIS study |
|
87 |
Re-enumeration complete, no eligible RU member,
Ineligible RU |
|
88 |
Unavailable during field period |
|
89 |
Too ill, No proxy |
|
90 |
Physical/Mental incompetent, No proxy |
|
91 |
Final Refusal |
|
92 |
Final Breakoff |
|
93 |
Unable to locate |
|
94 |
Entire RU is military or left U.S. AFTER 1/1/97 |
|
95 |
RU member institutionalized after
1/1/97, No proxy |
|
96 |
RU member deceased after 1/1/97, No proxy |
|
97 |
Re-enumeration complete, no RU member, Non-Response |
|
98 |
RU moved too far away to interview |
|
99 |
Final other Non-Response |
The values for RURSLT42 and RURSLT53 include the following: Return To Table Of Contents
|
-1 |
Inapplicable |
|
60 |
Complete with RU member |
|
61 |
Complete with proxy--all RU members deceased |
|
62 |
Complete with proxy--all RU members institutionalized
or deceased |
|
63 |
Complete with proxy, other |
|
70 |
Entire RU merged with other RU |
|
71 |
Re-enumeration complete, no eligible RU member,
Ineligible RU |
|
72 |
RU institutionalized in prior round; still
institutionalized |
|
81 |
Entire RU deceased before 1/1/97 |
|
82 |
Entire RU is in military BEFORE 1/1/97 |
|
83 |
RU institutionalized before 1/1/97 |
|
84 |
Entire RU left U.S. before 1/1/97 |
|
85 |
RU ineligible before 1/1/97, multi-reason |
|
86 |
RU ineligible, non-key NHIS study |
|
87 |
Language Barrier |
|
88 |
Unavailable during field period |
|
89 |
Too ill, No proxy |
|
90 |
Physical/Mental incompetent, No proxy |
|
91 |
Final Refusal |
|
92 |
Final Breakoff |
|
93 |
Unable to locate |
|
94 |
Entire RU is military or left U.S. AFTER 1/1/97 |
|
95 |
RU member institutionalized after
1/1/97, No proxy |
|
96 |
RU member deceased after 1/1/97, No proxy |
|
97 |
Re-enumeration complete, no RU member, Non-Response |
|
98 |
RU moved too far away to interview |
|
99 |
Final other Non-Response |
Standard, or primary RUs are the original RUs from NHIS. All
primary RUs are classified as standard RUs. A new RU is one created when members
of the household leave the primary RU and are followed according to the rules of
the survey. A student RU is an unmarried college student (under 24 years of age)
that is considered a usual member of the household (but was living away from
home while going to school) and was treated as a Reporting Unit (RU) separate
from their parents RU for the purpose of data collection. RUCLAS97 was set based
on the RUCLASS values from Rounds 3/1, 4/2, and 5/3. If the person was present
in the responding RU in Round 5/3, then RUCLAS97 was set to RUCLAS53. If the
person was not present in a responding RU in Round 5/3, but was present in Round
4/2, then RUCLAS97 was set to RUCLAS42. If the person was not present in either
Rounds 4/2 or 5/3, but was present in Round 3/1, then RUCLAS97 was set to
RUCLAS31. If the person was not linked to a responding RU during any round then
RUCLAS97 was set to -9. Return To Table Of Contents
Reference Period Dates
The reference period is the period of time for which data
were collected in each round for each person. The reference period dates were
determined during the interview for each person by the CAPI program. The
round-specific beginning reference period dates are included for each person.
These variables include BEGRFM31, BEGRFD31, BEGRFY31, BEGRFM42, BEGRFD42,
BEGRFY42, BEGRFM53, BEGRFD53, and BEGRFY53. The reference period for Round 1 for
most persons began on January 1, 1997 and ended on the date of the Round 1
interview. For RU members who joined later in Round 1, the beginning Round 1
reference date was the date the person entered the RU. For all subsequent
rounds, the reference period for most persons began on the date of the previous
round’s interview and ended on the date of the current round’s interview.
Persons who joined after the previous round’s interview had their beginning
reference date for the round set as the day they joined the RU.
The round specific ending reference period dates for Rounds
3/1, 4/2, and 5/3 as well as the end-of-year reference period end date variables
are also included for each person. These variables include ENDRFM31, ENDRFD31,
ENDRFY31, ENDRFM42, ENDRFD42, ENDRFY42, ENDRFM53, ENDRFD53, ENDRFY53, ENDRFM97,
ENDRFD97, and ENDRFY97. For most persons in the sample, the date of the
interview is the reference period end date. Note that the end date of the
reference period is prior to the date of the interview if the person was
deceased during the round, left the RU, or was institutionalized prior to that
round’s interview, or left the RU to join the military. Return To Table Of Contents
Reference Person Identifiers
The round specific variables REFPRS31, REFPRS42 and REFPRS53
and the end-of-year status variable REFPRS97 identify the reference person for
Rounds 3/1, 4/2 and 5/3, and as of December 31, 1997. In general, the reference
person is defined as the household member 16 years of age or older who owns or
rents the home. If more than one person meets this description, the household
respondent identifies one from among them. If the respondent was unable to
identify a person fitting this definition, the questionnaire asked for the head
of household and this person was then considered the reference person for that
RU. This information was collected in the Re-enumeration section of the CAPI
questionnaire.
Respondent Identifiers
The respondent is the person who answered the interview
questions for the reporting unit (RU). The round specific variables RESP31,
RESP42, and RESP53 and the end-of-year status variable RESP97 identify the
respondent for Rounds 3/1, 4/2, and 5/3 and as of December 31, 1997. Only one
respondent is identified for each RU. In instances where the interview was
completed in more than one session, only the first respondent is indicated.
There are two types of respondents. The respondent can be
either a RU member or a non-RU member proxy. The round specific variables
PROXY31, PROXY42, PROXY53 and the end-of-year status variable PROXY97 identify
the type of respondent for Rounds 3/1, 4/2, 5/3 and as of December 31, 1997.
Person Status
A number of variables describe the various components
reflecting each person’s status for each round of data collection. These
variables provide information about a person’s inscope status, Keyness status,
eligibility status, and disposition status. These variables include: INSCOPE,
INSCOP31, INSCOP42, INSCOP53, INSCOP97, KEYNESS, ELIGIBLE, ELGRND31, ELGRND42,
ELGRND53, ELGRND97, PSTATS31, PSTATS42, and PSTATS53. These variables are set
based on sampling information and responses provided in the re-enumeration
section of the CAPI questionnaire.
Through the re-enumeration section of the CAPI questionnaire,
each member of a reporting unit was classified as "key" or
"non-key", "inscope" or "out-of-scope", and
"eligible" or "ineligible" for MEPS data collection. To be
included in the set of persons used in the derivation of MEPS person level
estimates; a person had to be a member of the civilian non-institutionalized
population for at least one day during 1997. Because a person's eligibility for
the survey might have changed since the NHIS interview, a sampling
re-enumeration of household membership was conducted at the start of each round’s
interview. Only persons who were "inscope" sometime during the year,
"key", and responded for the full period in which they were inscope
were assigned positive person level weights and thus are to be used in the
derivation of person level national estimates from the MEPS.
Note: if analysts want to subset to infants born during 1997,
then newborns should be identified using AGE97X = 0 rather than PSTATS = 51. Return To Table Of Contents
Inscope
A person was considered as inscope during a round if he or
she was a member of the U.S. civilian, non-institutionalized population at some
time during that round. The round specific variables INSCOP31, INSCOP42, and
INSCOP53 indicate a person’s inscope status for rounds 3/1, 4/2, and 5/3.
INSCOP97 indicates a person’s inscope status for the portion of round 5/3 that
covers 1997. The values of these three variables taken in conjunction allow one
to determine inscope status over time (for example, becoming inscope in the
middle of a round, as would be the case for newborns). The INSCOPE variable
indicates whether a person was ever inscope during the calendar year 1997.
INSCOP31, INSCOP42, INSCOP53, and INSCOP97 will contain the following
values and corresponding label (for INSCOP97, "reference period" in
the description below is the portion of Round 5/3 in 1997):
0 |
Incorrectly listed, or on NHIS roster but out-of-scope
prior to January 1, 1997 |
|
1 |
Person is inscope for the whole reference period |
|
2 |
Person is inscope at the start of the RU reference
period, but not at the end of the RU reference period. |
|
3 |
Person is not inscope at the start of RU reference
period, but is inscope at the end of the RU reference period. (E.g., the
person is inscope from the date the person joined the RU or the person was
in the military in the previous round, but is no longer in the military in
the current round.) |
|
4 |
Person is inscope during the reference period, but
neither at the reference start date nor on the reference end date. (E.g.,
Person leaves an institution, goes into community, and then dies.) |
|
5 |
Person is out-of-scope for all of the reference period
during which they are in an RU member (i.e. The person is in the
military.) |
|
6 |
Person is out-of-scope for the entire reference period
and is not a member of the RU during this time period and was inscope and
an RU member in an earlier round. |
|
7 |
Person is not in an RU, joined in a later round (or
joined RU after December 31, 1997 for INSCOP97) |
|
8 |
RU Non-response and key persons who left an RU with no
tracing info and so a new RU was not formed |
|
9 |
Person is non-key or full time in the military, not a
member of an RU during this time period, and was an RU member in an
earlier round |
Return To Table Of Contents
Keyness
The term "keyness" is related to an individual’s
chance of being included in MEPS. A person is key if that person is linked for
sampling purposes to the set of NHIS sampled households designated for inclusion
in MEPS. Specifically, a key person was a member of an NHIS household at the
time of the NHIS interview, or became a member of such a household after being
out-of-scope at the time of the NHIS (examples of the latter situation include
newborns and persons returning from military service, an institution, or living
outside the United States).
A non-key person is one whose chance of selection for the
NHIS (and MEPS) was associated with a household eligible but not sampled for the
NHIS, and who later became a member of a MEPS reporting unit. MEPS data, (e.g.,
utilization and income) was collected for the period of time a non-key person
was part of the sampled unit to provide information for family level analyses.
However, non-key persons who leave a sample household unaccompanied by a key,
inscope member were not followed for subsequent interviews. Non-key individuals
do not receive sample person-level weights and thus do not contribute to person
level national estimates.
The variable KEYNESS indicates a person’s keyness status.
This variable is not round specific. Instead, it is set at the time the person
enters MEPS, and the person’s keyness status never changes. Once a person is
determined to be key, that person will always be key.
It should be pointed out that a person might be key even
though not part of the civilian, non-institutionalized portion of the U.S.
population. For example, a person in the military may have been living with his
or her civilian spouse and children in a household sampled for NHIS. The person
in the military would be considered a key person for MEPS; however, such
a person would not be eligible to receive a person-level sample weight if he or
she was never inscope during 1997. Return To Table Of Contents
Eligibility
The eligibility of a person for MEPS pertains to whether or
not data were to be collected for that person. All of the key, inscope, persons
of a sampled RU were eligible for data collection. The only non-key persons
eligible for data collection were those who happened to be living in a RU with
at least one key, inscope person. Their eligibility continued only for the time
that they were living with at least one such person. The only out-of-scope
persons eligible for data collection were those who were living with key inscope
persons, again only for the time they were living with such a person. Only
military persons can meet this description (for example, a person on full time
active duty military, living with a spouse who is key).
A person may be classified as eligible for an entire round or
for some part of a round. For persons who are eligible for only part of a round
(for example, persons may have been institutionalized during a round) data were
collected for that person only for the period of time for which that person was
classified as eligible. The round specific variables ELGRND31, ELGRND42,
ELGRND53 and the end-of-year status variable ELGRND97 indicate a person’s
eligibility status for Rounds 3/1, 4/2 and 5/3 and as of December 31, 1997. The
ELIGIBLE variable indicates if a person was ever eligible during the calendar
year 1997.
Person Disposition Status
The round-specific variables PSTATS31, PSTATS42, and PSTATS53
indicate a person’s response and eligibility status for each round of
interviewing. The PSTATS variables indicate the reasons for either continuing
data collection for a person or terminating data collection for each person in
the MEPS. Using this variable, one could identify persons who moved during the
reference period, died, were born, institutionalized or who were in the
military. Analysts should note that PSTATS53 provides a summary for all of Round
5/3, including transitions that occurred after 1997. However, PSTATS53 is still
a useful guide to following transitions that occur over time in the sample for
1997. Return To Table Of Contents
The following codes specify the value labels for the PSTATS variables.
|
-1 |
The person was not fielded during the round or the RU
was non-response |
|
0 |
Incorrectly listed in RU at NHIS -applies to MEPS Round
1 only |
|
11 |
Person in original RU , not full time active military
duty |
|
12 |
Person in original RU, full time active military duty,
out-of-scope for whole reference period. |
|
13 |
Full time student living away from home, but associated
with sampled RU |
|
14 |
The person is full time active military duty during
round and is inscope for part of the reference period and is in the RU at
the end of the reference period |
|
21 |
The person remains in a health care institution for the
whole round - rounds 4/2 and 5/3 only |
|
22 |
The person leaves a health care
institution and rejoins the community - rounds 4/2 and 5/3 only |
|
23 |
The person leaves a health care institution, goes into
community and then dies - rounds 4/2 and 5/3 only |
|
24 |
The person dies in a health care institution during the
round (former RU member) - rounds 4/2 and 5/3 only |
|
31 |
Person from original RU, dies during reference period |
|
32 |
Went to health care institution during reference period |
|
33 |
Went to non-healthcare institution during reference
period |
|
34 |
Moved from original RU, outside U.S. (not as student) |
|
35 |
Moved from original RU, to a military facility while on
full time active military duty |
|
36 |
Went to institution (type unknown) during reference
period |
|
41 |
Moved from the original RU, to new RU within U.S. (new
RUs include RUs originally classified as "Student RU" but which
converted to "New RU") |
|
42 |
The person joins RU and is not full time military
during round |
|
43 |
The person's disposition as to why the person is not in
the RU is unknown or the person moves and it is unknown whether the person
moved inside or outside the U.S. |
|
44 |
The person leaves an RU and joins an existing RU and is
not both in the military and coded as inscope during the round |
|
51 |
Newborn in reference period |
|
61 |
Died prior to reference period (not eligible)-Round 1
only |
|
62 |
Institutionalized prior to reference period (not
eligible)-Round 1 only |
|
63 |
Moved outside U.S., prior to reference period (not
eligible)-Round 1 only |
|
64 |
Full time military, living on a military facility,
moved prior to reference period (not eligible)-Round 1 only |
|
71 |
Student under 24 living away at school in grades 1-12
(non-key) |
|
72 |
Person is dropped from the RU roster as ineligible: the
person is a non-key student living away or the person is not related to
reference person or the RU is the person's residence only during the
school year |
|
73 |
Not key and not full-time military, moved w/o someone
key and inscope (not eligible) |
|
74 |
Moved as full-time military but not to a military
facility and w/o someone key and inscope (not eligible this round) |
|
81 |
Person moved from original RU, full time student living
away from home, did not respond |
In addition, the variable INRU1231 indicates if a person was
present in the RU on December 31, 1997. Persons living in the RU as well as any
person coded as "living away in grades 1-12" will have a value of
"1" indicating "Yes, the person was present on December 31,
1997."
Return To Table Of Contents
2.5.2
Navigating the MEPS Data with Information on Person Disposition Status
Since the variables PSTATS31, PSTATS42, and PSTATS53 indicate
the reasons for either continuing or terminating data collection for each person
in MEPS, these variables can be used to explain the beginning and ending dates
for each individual’s reference period of data collection, as well as which
sections in the instrument each individual received. By using the information
included in the table below, analysts will be able to determine for each
individual which sections of the MEPS questionnaire collected data elements for
that person.
Some individuals have a reference period that spans an entire
round, while other individuals may have data collected only for a portion of the
round. When an individual’s reference period does not coincide with the RU
reference period, the individual’s start date may be a later date, or their
end date may be an earlier date, or both. In addition, some individuals have
reference period information coded as inapplicable (e.g., for individuals who
were not actually in the household). The information in this table indicates the
beginning and ending dates of reference periods for persons with various values
of PSTATS31, PSTATS42, and PSTATS53. The actual dates for each individual can be
found in the following variables included on this file: BEGRFM31, BEGRFM42,
BEGRFM53, BEGRFD31, BEGRFD42, BEGRFD53, BEGRFY31, BEGRFY42, BEGRFY53, ENDRFM31,
ENDRFM42, ENDRFM53, ENDRFD31, ENDRFD42, ENDRFD53, ENDRFY31, ENDRFY42, ENDRFY53,
ENDRFM97, ENDRFD97, and ENDRFY97.
The table below also describes the section or sections of the
questionnaire, which were NOT asked for each value of PSTATS31, PSTATS42,
and PSTATS53. For example, the condition enumeration (CE) and
alternative/preventive care (AP) sections have questions, which are not asked
for deceased persons. The closing section (CL) also contains some questions or
question rosters (see CL06A, CL35 through CL37, CL48 through CL50, CL54, CL58,
and CL64) that exclude certain persons depending on whether the person died,
became institutionalized, or otherwise left the reporting unit; however, no one
is considered to have skipped the entire section. Some questions or sections
(e.g., health status (HE), employment (RJ, EM, EW)) are skipped if individuals
are not within a certain age range. Since the PSTATS variables do not address
skip patterns based on age, analysts will need to use the appropriate age
variables.
Please note that the end reference date shown below for
PSTATS53 reflects the Round 5/3 reference period rather than the portion of
Round 5/3 that occurred during 1997.
|
PSTATS Value |
PSTATS
Description |
Sections in the instrument which persons with this
PSTATS value do NOT receive |
Begin Reference Date |
End
Reference Date |
|
-1 |
The person was not fielded during the round or the RU was non-response |
ALL sections |
Inapplicable |
Inapplicable |
|
0 |
Incorrectly listed in RU at NHIS - Round 3/1 only |
ALL sections after RE |
Inapplicable |
Inapplicable |
|
11 |
Person in original household, not FT active military duty (Person is in
the same RU as the previous round) |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Interview date |
|
12 |
Person in original household, FT active military duty, out-of-scope for
whole reference period. |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Interview date |
|
13 |
FT student living away from home, but associated with sampled household |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Interview date |
|
14 |
The person is FT active military duty during round and is inscope for
part of the reference period and is in the RU at the end of the reference
period |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
PSTATS31: Interview date
PSTATS42 and PSTATS53: If the person is living w/ someone key and
inscope, then the interview date. If not living w/ someone who is key and
inscope, then the date the person joined the military |
|
21 |
The person remains in a health care institution for the whole round -
rounds 4/2 and 5/3 only |
All sections after RE |
Inapplicable |
Inapplicable |
|
22 |
The person leaves a health care institution and rejoins the community -
rounds 4/2 and 5/3 only |
-- |
Date rejoined the community |
Interview date |
|
23 |
The person leaves a health care institution, goes into community and
then dies - rounds 4/2 and 5/3 only |
Part of CE - Condition enumeration: Skip CE1 to CE5
HE - Health status
AC - Access to care
Part of AP - Alternative/Preventive care: Skip AP12 to AP22 |
Date rejoined the community |
Date of Death |
|
24 |
The person dies in a health care institution during the round (former
household member) - rounds 4/2 and 5/3 only |
All sections after RE |
Inapplicable |
Inapplicable |
|
31 |
Person from original household, dies during reference period |
Part of CE - Condition enumeration: Skip CE1 to-CE5
HE - Health status
AC - Access to care
Part of AP - Alternative/Preventive care: Skip AP12 to AP22 |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date of Death |
|
32 |
Went to healthcare institution during reference period |
Access to care (AC) |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date institutionalized |
|
33 |
Went to non-healthcare institution during reference period |
Access to care (AC) |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date institutionalized |
|
34 |
Moved from original household, outside US |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date left the RU |
|
35 |
Moved from original household, to a military facility while on FT
active military duty |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date left the RU |
|
36 |
Went to institution (type unknown) during reference period |
Access to care (AC) |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Date institutionalized |
|
41 |
Moved from the original household, to new household within US (new
households include RUs originally classified as a student RU but which
converted to a new RU. These are individuals in an RU that has split from
an RU since the previous round |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Interview date |
|
42 |
The person joins household and is not full time military during round |
-- |
The later date of January 1, 1997 and the date the person joined the RU |
Interview date |
|
43 |
The person’s disposition as to why the person is not in the RU is
unknown or the person moves and it is unknown whether the person moved
inside or outside the U.S. |
All sections after RE |
Inapplicable |
Inapplicable |
|
44 |
The person leaves an RU and joins an existing RU and is not both in the
military and coded as inscope during the round |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date of the RU the person
has joined. This may not be the interview date of the RU that the person
came from |
Interview date |
|
51 |
Newborn in reference period |
Questions where age must be > 1
(see Health status (HE),
Disability days (DD)
Employment (RJ/EM/EW) will be skipped |
PSTATS31: January 1, 1997 if born prior to 1997. The date of birth if
born in 1997.
PSTATS42 and PSTATS53: The later of the Prior round interview date and
date of birth |
Interview date |
|
61 |
Died prior to reference period (not eligible)--Round 3/1 only |
All sections after RE |
Inapplicable |
Inapplicable |
|
62 |
Institutionalized prior to reference period (not eligible)--Round 3/1
only |
All sections after RE |
Inapplicable |
Inapplicable |
|
63 |
Moved outside U.S., prior to reference period (not eligible)--Round 3/1
only |
All sections after RE |
Inapplicable |
Inapplicable |
|
64 |
FT military, moved prior to reference period (not eligible)--Round 3/1
only |
All sections after RE |
Inapplicable |
Inapplicable |
|
71 |
Student under 24 living away at school in grades 1 thru 12 (non-key) |
-- |
PSTATS31: January 1, 1997
PSTATS42 and PSTATS53: Prior round interview date |
Interview date |
|
72 |
Person is dropped from the RU roster as ineligible: the person is a
non-key student living away or the person is not related to reference
person or the RU is the person’s residence only during the school year |
All sections after RE |
Inapplicable |
Inapplicable |
|
73 |
Not key and not full-time military, moved w/o someone key and inscope
(not eligible) |
All sections after RE |
Inapplicable |
Inapplicable |
|
74 |
Moved as full-time military but not to a military facility and w/o
someone key and inscope (not eligible) |
All sections after RE |
Inapplicable |
Inapplicable |
|
81 |
Person moved from original household, FT student living away from home,
did not respond |
No data was collected |
Inapplicable |
Inapplicable |
2.5.3 Geographic Variables
The round-specific variables REGION31, REGION42, REGION53,
and the end-of-year status variable REGION97 indicate the Census region for the
RU. REGION97 indicates the region for the 1997 portion of Round 5/3. For most
analyses, REGION97 should be used. The round-specific variable MSA53 and the
end-of-year status variable MSA97 indicate whether or not the RU is found in a
metropolitan statistical area. MSA53 indicates the MSA status at the time of the
Round 5/3 interview. MSA97 indicates the MSA status for the 1997 portion of
Round 5/3. For most analyses, analysts should use MSA97 rather than MSA53. Return To Table Of Contents
2.5.4 Demographic Variables
General Information
Demographic variables provide information about the
demographic characteristics of each person from the MEPS-HC. The characteristics
include age, sex, race, ethnicity, educational attainment, marital status, and
military service. As noted below, some variables have edited and imputed values.
Most demographic variables on this file are asked during every round of the MEPS
interview. These variables describe data for Rounds 3, 4, and 5 of Panel 1 (1996
Panel); Rounds 1, 2 and 3 of Panel 2 (1997 Panel); and status as of December 31,
1997. Demographic variables that are round specific are identified by names
including numbers "xy," where x and y refer to
Round numbers of Panels 1 and 2 respectively. Thus, for example, AGE31X
represents the age data relevant to Round 3 of Panel 1 or Round 1 of Panel 2. As
mentioned in Section 2.5.1 Survey Administrative Variables, the variable PANEL97
indicates from which Panel the data were derived. A value of 1 indicates Panel 1
data and a value of 2 indicates Panel 2 data. The remaining demographic
variables on this file are not round specific.
The variables describing demographic status of the person as
of December 31, 1997 were developed in two ways. First, the age variable
(AGE97X) represents the exact age as of 12/31/97, calculated from date of birth.
For the remaining December 31st variables [i.e., related to marital
status (MARRY97X, SPOUID97, SPOUIN97), educational attainment (EDUCYR97,
HIDEG97), student status (FTSTUD97X) and the relationship to reference persons
(RFREL97X)], the following algorithm was used: data were taken from Round 5/3
counterpart if non-missing; else, if missing, data were taken from the Round 4/2
counterpart; else from the Round 3/1 counterpart. If no valid data was available
during any of these Rounds of data collection, the same algorithm was followed
to assign a missing value other than -1 (Inapplicable).
Age
Date of birth and age for each RU member were asked or
verified during each MEPS interview
(DOBMM, DOBYY, AGE31X, AGE42X, AGE53X). If date of birth was
available, age was calculated based on the difference between date of birth and
date of interview (or the date of death, if the person died prior to the
interview date). Inconsistencies between the calculated age and the age reported
during the CAPI interview were reviewed and resolved. For purposes of
confidentiality, the variables AGE31X, AGE42X, AGE53X and AGE97X were top coded
at 90 years.
When date of birth was not provided but age was provided
(either from the MEPS interviews or the 1995-1996 NHIS data), the month and year
of birth were assigned randomly from among the possible valid options. For any
cases still not accounted for, age was imputed using
- the mean age difference between MEPS participants with certain family
relationships (where available) or
- the mean age value for MEPS participants.
For example, a mother’s age is imputed as the average age
of her children plus 26, where 26 is the mean age difference between MEPS
mothers and their children. Or a wife’s age is imputed as the husband’s age
minus 3, where 3 is the mean age difference between MEPS wives and husbands.
Age was imputed in this way for 20 persons on this file. Return To Table Of Contents
Sex
Data on the sex of each RU member (SEX) were initially
determined from the 1995 NHIS for Panel 1 and from the 1996 NHIS for Panel 2.
The SEX variable was verified and, if necessary, corrected during each MEPS
interview. The data for new RU members (persons who were not members of the RU
at the time of the NHIS interviews) was also obtained during each MEPS Round.
When sex of the RU member was not available from the NHIS interviews and was not
ascertained during one of the subsequent MEPS interviews, it was assigned in the
following way. The person’s first name was used to assign sex, if obvious (25
cases were resolved in this way). If the person’s first name provided no
indication of gender, then family relationships were reviewed (11 cases). If
neither of these approaches made it possible to determine the individual’s
sex, sex was randomly assigned (3 cases).
Race, Race/Ethnicity, Hispanic
Ethnicity, and Hispanic Ethnicity Group
Race (RACEX) and Hispanic ethnicity (HISPANX) questions were
initially asked for each RU member during the Round 1 MEPS interview. If this
information was not obtained in Round 1, the questions were asked in subsequent
Rounds. When race and/or ethnicity was not reported in the Rounds, values for
these variables were obtained based on the following priority order. When
available, they were obtained from the originally collected NHIS data (1995 or
1996, depending on the Panel). If not ascertained, the race, and/or ethnicity
were assigned based on relationship to other members of the RU using a priority
ordering that gave precedence to blood relatives in the immediate family. This
approach was used in the resolution of a residual group of 24 cases, 17 of which
were missing both race and ethnicity and 7 of which were missing only ethnicity.
The variable RACETHNX indicating both race and ethnicity (e.g., with categories
such as "Hispanic" and "black but not Hispanic") reflects
the imputations done for RACEX and HISPANX. The specific Hispanic ethnicity
group is given in the unedited variable HISPCAT. Return To Table Of Contents
Marital Status and Spouse ID
Current marital status was collected and/or updated during
every Round of the MEPS interview. This information was obtained in RE13 and
RE97 and is reported as MARRY31X, MARRY42X, MARRY53X and MARRY97X. Persons under
the age of 16 were coded as 6 (under 16 – inapplicable). If marital status of
a specified round differed from that of the previous Round, then the marital
status of the specified Round was edited to reflect a change during the Round
(e.g., married in Round, divorced in Round, separated in Round, or widowed in
Round).
In instances where there were discrepancies between the
marital status of two individuals within a family, other person-level variables
were reviewed to determine the edited marital status for each individual. Thus,
when one spouse was reported as married and the other spouse reported as
widowed, the data were reviewed to determine if one partner should be coded as 8
(widowed in Round).
Four edits were performed to ensure minimal
consistency across rounds. First, a person could not be coded as
"Never Married" after previously being coded as any other marital
status (e.g. "Widowed"). Second, a person could not be coded as
"Under 16 – Inapplicable" after being previously coded as any other
marital status. Third, a person could not be coded as "Married in
Round" after being coded as "Married" in the Round immediately
preceding. Fourth, a person could not be coded as an "in Round" code
(e.g., "widowed in Round") in two subsequent Rounds. Because no other
edits were performed, and since marital status can change across Rounds,
unlikely sequences for marital status across the Round-specific variables do
exist.
The person identifier for each individual’s spouse is
reported in SPOUID31, SPOUID42, SPOUID53 and SPOUID97. These are the PIDs
(within each family) of the person identified as the spouse during Round 3/1,
Round 4/2, Round 5/3 and as of December 31, 1997, respectively. If no spouse was
identified in the household, the variable was coded as 995 (No spouse in
household). Those with unknown marital status are coded as 996 (Marital status
unknown). Persons under the age of 16 are coded as 997 (Less than 16 years old).
The SPOUIN31, SPOUIN42, SPOUIN53 and SPOUIN97 variables
indicate whether a person’s spouse was present in the RU during Round 3/1,
Round 4/2, Round 5/3 and as of December 31, 1997 respectively. If the person had
no spouse in the household, the value was coded as 2 (Not married/No spouse).
For persons under the age of 16 the value was coded as 3 (Under 16 –
Inapplicable).
The SPOUID and SPOUIN variables were obtained from RE76 and
RE77, where the respondent was asked to identify how each pair of persons in the
household were related. Analysts should note that this information was collected
in a set of questions separate from the questions that asked about marital
status. While editing was performed to ensure that SPOUID and SPOUIN are
consistent within each Round, there was no consistency check between these
variables and marital status in a given Round. Apparent discrepancies between
marital status and spouse information may be due to any of the following causes:
Ambiguity as to when during a Round a change in marital
status occurred. This is a result of relationship information being asked
for all persons living in the household at any time during the Round, while
marital status is asked as of the interview date (e.g., If one spouse died
during the reference period, the surviving spouse’s marital status would
be "widowed in Round", but SPOUIN and SPOUID for the same round
would indicate that a spouse was present).
Valid discrepancies in the case of persons who are
married but not living with their spouse, or separating but still living
together.
Discrepancies that cannot be explained for either of the
previous reasons. Return To Table Of Contents
Student Status and Educational Attainment
The variables FTSTU31X, FTSTU42X, FTSTU53X and FTSTU97X
indicate whether the person was a full-time student at the interview date (or
12/31/97 for FTSTU97X). These variables have valid values for all persons
between the ages of 17 - 23 inclusive. When this question was asked during Round
1 of Panel 2, it was based on age as of the 1996 NHIS interview date; for
persons who were 17 years old at the Round 1 but 16 years old at the time of the
NHIS, FTSTU31X was set to -9 (Not ascertained) resulting in a large number of -9
values.
Completed years of education are indicated in the variables
EDUCYR31, EDUCYR42, EDUCYR53 and EDUCYR97. Information was obtained from
questions RE 103-105. Children who are 5 years of age or older and who never
attended school were coded as 0; children under the age of 5 years were coded as
-1 (Inapplicable) regardless of whether or not they attended school. However,
among the cases coded as inapplicable, there is no distinction between those who
were under the age of five and others who were inapplicable, such as persons who
may be institutionalized for an entire round.
The variables indicating highest degree (HIDEG31, HIDEG42,
HIDEG53 and HIDEG97) were obtained from three questions: highest grade completed
(RE103), high school diploma (RE 104) and highest degree (RE 105). Persons under
16 years of age were coded as 8 (Under 16- Inapplicable). In cases where the
response to the highest degree question was "No degree" and the
response to the highest grade question was 13 through 17 (1 or more years of
college), the variable HIDEG was coded as 3 (high school diploma). If highest
grade completed was "refused" or "don’t know" for those
with a "No degree" response for the highest degree question, the
variable HIDEG was coded as 1 (no degree).
The user should note that the EDUCYR and HIDEG variables are
unedited variables and minimal data cleaning was performed on these variables.
Therefore, discrepancies across rounds of data remain for these two sets of
variables. Decisions as to how to handle these discrepancies are left to the
analyst. Return To Table Of Contents
Military Service and Service Era
Information on active duty military status was collected
during each Round of the MEPS interview. Persons currently on full-time active
duty status are identified in the variables ACTDTY31, ACTDTY42, and ACTDTY53.
Those under 16 years of age were coded as 3 (Under 16 – Inapplicable) and
those over the age of 59 were coded as 4 (Over 59 – Inapplicable).
The variable DIDSERVE is only collected during Round 1 of the
MEPS interview. It indicates if the person ever served in the Armed Forces.
Persons under the age of 16 were coded as 3 (Under 16 – Inapplicable).
Individuals currently on active duty military service were coded as 4 (Now
active duty). Those individuals entering a MEPS household after Round 1 have
DIDSERVE set to –1 (Inapplicable). Like DIDSERVE, data on service in specific
eras was only collected during Round 1 of the MEPS interview. Individuals who
were ever in the military based on the DIDSERVE and ACTDTY question(s) of Round
1 were also asked if they served in either World War I or World War II (VETWW),
the Korean War era (VETKOR), the Vietnam War era (VETVIET), the Post-Vietnam War
era (VETPVIET), or another service era (VETOTH). Those under the age of 16 were
coded as 3 (Under 16 –Inapplicable) and those who never served in the military
were coded as 4 (Never in military). Persons entering a MEPS household
after Round 1 have these variables set to –1 (Inapplicable).
Because DIDSERVE and veteran status variables are only asked during Round 1,
and because the 1997 FY file only contains data from Rounds 3, 4, and 5 of Panel
1, these variables would have been missing for persons in Panel 1. Consequently,
an analyst would have had to go back to the 1996 full year file (MEPS HC-008) in
order to determine the military service and veteran status values for those
Panel 1 persons. Therefore, to provide a better estimation of military service
and veteran status for this 1997 full year file, DIDSERVE, VETWW, VETKOR,
VETVIET, VETPVIET, and VETOTH from Panel 1, Round 1 (on the 1996 file) were
brought forward onto the 1997 Full Year file.
The user should note that the DIDSERVE and veteran status
variables were reviewed for consistency. The veteran status variables were
minimally edited to ensure that all individuals under 16 years of age were coded
as 3 (Under 16 – Inapplicable) for the specific veteran-era variables.
However, no other age editing was performed, and, thus, it is possible for
age/era inconsistencies to exist (e.g., AGE31X=17 and VIETVET=Yes). Return To Table Of Contents
Relationship to the Reference Person
within Reporting Units
For each reporting unit (RU), the person who owns or rents
the dwelling unit is usually defined as the reference person. For student RUs,
the student is defined as the reference person. (For additional information on
reference persons, see the documentation on survey administration variables.)
The variables RFREL31X, RFREL42X, RFREL53X and RFREL97X indicate the
relationship of each individual to the reference person of the reporting unit
(RU) in a given round. For the reference person, this variable has the value
"self;" for all other persons in the RU, relationship to the reference
person is indicated by codes representing "husband/spouse,"
"wife/spouse," "son," "daughter," "female
partner," "male partner," etc. A code of 91, meaning "other
related, specify," was used to indicate rarely observed relationship
descriptions such as "mother of partner." If the relationship of an
individual to the reference person was not ascertained during the Round-specific
interview, relationships between other RU members were used, where possible, to
assign a relationship to the reference person. If MEPS data from calendar year
1997 were not sufficient to identify the relationship of an individual to the
reference person, relationship variables from the 1996 MEPS or NHIS data were
used to assign a relationship. In the event that a meaningful value could not be
determined or data were missing, the relationship variable was assigned a
missing value code.
For 339 cases, where two individual’s relationship
indicated they were spouses, but both had marital status indicating they were
not married, their relationship was changed to non-marital partners. In
addition, the relationship variables were edited to insure that they did not
change across rounds for RUs in which the reference person did not change, with
the exception of relationships identified as partner, spouse, or foster
relationships.
Parent Identifiers
The variables MOPID31X, MOPID42X, MOPID53X and DAPID31X,
DAPID42X DAPID53X are round specific and are used to identify the parents
(biological, adopted, or step) of the person represented on that record.
MOPID##X contains the person identifier (PID) for each individual’s mother if
she lived in the dwelling unit in that panel/round of the survey, or a value of
–1 (Inapplicable) if she did not. Similarly, DAPID##X contains the person
identifier (PID) for each individual’s father if he lived in the dwelling unit
in that panel/round of the survey, or a value of –1 (Inapplicable) if he did
not. MOPID##X and DAPID##X were constructed based on information collected in
the relationship grid of the instrument each round at questions RE76 and RE77
and include biological, adopted, and step parents. Foster parents were not
included.
Edits were performed to ensure that MOPID##X and DAPID##X
were consistent with each individual’s age, sex, and other relationships
within the family. For instance, the gender of the parent must be consistent
with the indicated relationship; mothers are at least 12 years older than the
person and no more than 55 years older than the person; fathers are at least 12
years older than the person; each person has no more than one mother and no more
than one father; any values set for MOPID##X and DAPID##X were removed from any
person identified as a foster child; and the PID for the person’s mother and
father are valid PIDS for that person’s DU in that round. For persons who were
not present in the household during a round, MOPID##X and DAPID##X have values
of –1 (Inapplicable). Return To Table Of Contents
2.5.5
Income and Tax Filing Variables
The file provides income and tax-related variables that were
constructed primarily from data collected in the Round 3 Income Section.
Person-level income amounts have been edited and imputed for every record on the
full-year file, with detailed imputation flags provided as a guide to the method
of editing. The tax-filing variables and some program participation variables
are unedited as discussed below.
Logical editing or weighted, sequential hot-deck imputation
was used to impute income amounts for missing values (both for item non-response
and for persons in the full-year file who were not in Round 3). Reported income
components were generally left unedited (with the few exceptions noted below).
Thus, analysts using these data may wish to apply additional checks for outlier
values that would appear to stem from mis-reporting.
The editing process began with wage and salary income,
WAGEP97X. Complete responses were left unedited, and this group of people was
assigned WAGEIMP97 = 1, where WAGEIMP97 is the imputation flag for wage and
salary data. The only exception was for a small number of persons who reported
zero wage and salary income despite having been employed for pay during the year
according to round level data (see below). Since data on tax filing and on
taxable income sources were collected using an approach that encouraged
respondents to provide information from their federal tax returns, logical edits
were used to assign separate income amounts to married persons whose responses
were based on combined income amounts on their joint tax returns.
Persons assigned WAGIMP97=2 were those providing broad income
ranges rather than giving specific dollar amounts. Weighted sequential
hot-decking was used to provide these individuals with specific dollar amounts.
For this imputation, donors were persons who reported specific dollar amounts
within the corresponding broad income ranges. All WAGEP97X hot-deck imputations
used cells defined on the basis of a conventional list of person-level
characteristics including age, education, employment status, race, sex, and
region.
Persons assigned WAGIMP97=3 were those who did not report
wage and salary income and who were assigned WAGEP97X=0 based on either being
under 16 or not having been employed during the year.
Persons assigned WAGIMP97=4 were those who did not provide
valid dollar amounts or dollar ranges, but for whom we had information from the
employment sections of Rounds 1, 2, and 3 concerning wages, hours, and weeks
worked (in all jobs). These data were used to construct annualized wage amounts
to be used in place of missing annual wage and salary data. Comparisons of
reported and constructed wages and salaries using persons who provided both
sorts of information made us highly confident that employment data could be
reliably used to derive values to serve in place of missing wage and salary
information (the two measures were highly correlated and the means differed by
less than $20). To implement this approach, part-year responders were assumed to
be fully-employed during the remainder of the year if they were employed during
the period in which they provided data. An exception was made for those who
either died or were institutionalized. These persons were assigned zero wages
and salaries for the time they were not in MEPS.
Hot deck imputation was used for the remaining persons with
missing WAGEP97X. Donor pools included persons whose WAGEP97X amounts were
edited in the steps described above. Whenever possible, the hot-deck imputations
used data on whether or not the person had been employed at any point during the
year (and, if available, the number of weeks worked). Imputations for persons
deemed to have been employed were conditional in nature, using only donors with
positive WAGEP97X amounts (WAGIMP97=5). Imputations for WAGEP97X for the
remaining persons were unconditional, using both workers and non-workers as
donors (WAGIMP97=6). Return To Table Of Contents
Having edited WAGEP97X for all persons in the full-year file,
we then edited the remaining income sources in the following sequence: INTRP97X,
BUSNP97X, FARMP97X, DIVDP97X, REFDP97X, ALIMP97X, SALEP97X, TRSTP97X, PENSP97X,
IRASP97X, SSECP97X, UNEMP97X, WCMPP97X, VETSP97X, CASHP97X, OTHRP97X, CHLDP97X,
SSIP97X, and PUBP97X. Income components were edited sequentially, in each case
using information regarding income amounts that had already been edited (so as
to maintain patterns of correlation across income sources whenever possible). In
all cases, bracketed responses were edited first (using hot-deck imputations
from donors in corresponding brackets who gave specific dollar amounts),
followed by imputations for remaining missing values. The hot-deck imputations
used cells defined on the basis of income amounts already edited and a
conventional list of person-level characteristics such as age, education,
employment status, race, sex, and region. In addition, hot-deck imputations for
CHLDP97X used family-level information concerning marital status and the number
of children. Hot-deck imputations for SSIP97X and PUBP97X were also assigned
using, in part, simulated program eligibility indicators that integrated
state-level program eligibility criteria with data on family composition and
income.
Reported income amounts of less than one dollar were treated
as missing amounts (to be hot-decked from donors with positive amounts of the
corresponding income source). Also, a very few cases of outlier responses were
edited (primarily public sources of income that exceeded possible amounts). With
only one other exception, reported income amounts were left unchanged. The
exception was Social Security Income, SSECP97X, which was under-reported in the
MEPS relative to the March 1998 Current Population Survey (CPS). Comparison with
the CPS identified the source of the MEPS under-reporting to be persons aged 65
and older who failed to report any SSECP97X despite having also reported no
earned income. Persons over 65 with neither earnings nor Social Security income
are quite rare in the CPS, giving us confidence in editing these responses.
Using the CPS, a probabilistic model was developed to select persons/couples
whose values of SSECP97X were changed from zero to a positive (imputed) amount.
For all of the income components, xxIMP97 variables
contain indicators concerning the method for editing/imputation. All the flag
variables have the following formatted values:
- 1=Original response used;
- 3=Missing value set to 0;
- 4=Weeks worked/earnings used (WAGIMP97 only);
- 6=Unconditional hot-deck.
Missing values were set to zero when there were too few
recipients to warrant hot-deck imputations of positive values (as in the case of
ALIMP97X received by males or WAGEP97X received by persons under age 16).
"Conditional hot-decks" indicate instances where the respondent
indicated receipt but not a specific dollar amount. In these cases, the donor
pool was restricted to persons with nonzero amounts of the income source in
question. "Unconditional hot-decks" indicate instances where the donor
pool included persons receiving both zero and nonzero amounts (implemented in
cases where we had little or no information about a person’s income source).
Total person-level income (TTLP97X) is the sum of all income
components with the exception of REFDP97X and SALEP97X (so that we are following
as closely as possible the CPS definition of income). Some researchers may wish
to define their own income measure by adding in one or both of these excluded
components.
The tax variables, food stamp variables, SSI disability flag,
and AFDC participation flag are all completely unedited. In particular, while
the tax variables are provided to assist researchers building tax simulation
programs, there is substantial item non-response. No effort was made to
eliminate inconsistencies with other MEPS data. All of these unedited variables
should be used with great care. Return To Table Of Contents
2.5.5.1
Income Top-Coding
All income amounts on the file, including both total income
and the separate sources of income, were top coded to preserve confidentiality.
For each income source, top codes were applied to the top percentile of all
cases (including negative amounts that exceeded income thresholds in absolute
value). In cases where fewer than one percent of all persons received a
particular income source, we top-coded all recipients. Top-coded income amounts
were masked using a regression-based approach. The regressions relied on many of
the same variables used in the hot-deck imputations, with the dependent variable
in each case being the natural logarithm of the amount that the income component
was in excess of its top-code threshold. Predicted values from this regression
were reconverted from logarithms to levels using a smearing correction, and
these predicted amounts were then added back to the top-code thresholds. This
approach preserves the component-by-component weighted means (both overall and
among top-coded cases), while also preserving much of the income distribution
conditional on the variables contained in our regressions. At the same time,
this approach ensures that every reported amount in excess of its respective
threshold is altered on the public use file. The process of top-coding income
amounts in this way inevitably introduces measurement error in cases where
income amounts were reported correctly by respondents. Note, however, that
top-coding can also help to reduce the impact of outliers that occur due to
mis-reporting.
Total income is constructed as the sum of the adjusted income
components. Having constructed total income in this manner, we then top-coded
this total using the same regression-based procedure described above (again
masking the top percentile of cases). Finally, we scaled the components of
income up or down in order to make the sources of income consistent with the
newly-adjusted totals. Return To Table Of Contents
2.5.5.2 Poverty Status
The file includes a categorical variable for 1997 family
income as a percentage of poverty (POVCAT97). This variable was constructed
primarily from data collected in the Round 3 Income Section. Logical editing or
weighted, sequential hot-deck imputation was used to impute income amounts for
missing values (both for item non-response and or persons in the full-year file
who were not in Round 3). Round-level data on employment status, hours worked,
and wages were used to supplement earnings data collected in the Income Section.
Family income was derived by constructing person-level total income comprising
annual earnings from wages, salaries, bonuses, tips, commissions; business and
farm gains and losses; unemployment and workman’s compensation; interest and
dividends; alimony, child support, and other private cash transfers; private
pensions, IRA withdrawals, social security, and veterans payments; supplemental
security income and cash welfare payments from public assistance, Aid to
Families with Dependent Children, and Aid to Dependent Children; gains or losses
from estates, trusts, partnerships, S corporations, rent, and royalties; and a
small amount of "other"income. Family income excluded tax refunds and
capital gains. Person-level income totals were then summed over family members
as defined by CPSFAMID to yield the family-level total. POVCAT97 is constructed
by dividing family income by the applicable poverty line (based on family size
and composition), with the resulting percentages grouped into 5 categories;
negative or poor (less than 100%), near poor (100 to less than 125%), low income
(125 to less than 200%), middle income (200 to less than 400%), and high income
(400%+). Persons missing CPSFAMID were treated as one-person families in
constructing POVCAT97. Family income as well as the components of person level
income have been subjected to internal editing patterns and derivation methods
that are in accordance to specific definitions, and are not being released at
this time. Researchers working with a family definition other than CPSFAMID may
wish to create their own versions of total family income (and perhaps POVCAT97). Return To Table Of Contents
2.5.6 Employment Variables
Employment questions were asked of all persons 16 years and
older at the time of the interview. Employment variables consist of person-level
indicators such as employment status and job-related variables such as hourly
wage. All job-specific variables refer to a person’s current main job. The
current main job, defined by the respondent, indicates the main
source of employment.
Most employment variables pertain to the round interview
date. The round dates are indicated by two numbers following the variable name;
the first number representing the round for Panel 1 persons, the second number
representing the round for Panel 2 persons. For example, EMPST31 refers to
employment status on the Round 3 interview date for Panel 1 persons and
employment status on the Round 1 interview date for Panel 2 persons.
With the exception of health insurance held or offered from a
current main job, no attempt has been made to logically edit any employment
variables. When missing, values were imputed for certain persons’ hourly
wages; however, there was no editing performed on any values reported by the
respondent. Due to confidentiality concerns, hourly wages greater than or equal
to $43.75 were top-coded to –10 and the number of employees variable was
top-coded at 500. With the exception of a variable indicating whether the
employer has more than one location (MORE), all employer-specific variables
refer to the establishment that is the location of a person’s current main
job.
The MEPS employment section used dependent interviewing in Rounds 2 through
5. If employment status and certain job characteristics did not change from the
previous round, the respondent was skipped through the employment section. A
code of "–2" is used to indicate that the information in question
was obtained in a previous round. For example, if the HRWG42X (Round 4 interview
date hourly wage for Panel 1 persons/Round 2 interview date hourly wage for
Panel 2 persons) is coded as -2, refer to HRWG31X (Round 3 interview date hourly
wage for Panel 1 persons/Round 1 interview date hourly wage for Panel 2 persons)
for the value for HRWG42X. Note that there may be a value for the Round 3/1
hourly wage or there may be an inapplicable code. The –2 value for HRWG42X
simply indicates that the person was skipped past the question at the time of
the interview. Obviously, to determine who should be skipped through various
employment questions, certain information, such as employment status, had to be
asked in every round and, thus, -2 codes do not apply to employment status.
Additionally, information on whether the person currently worked at more than
one job or whether the person held health insurance from a current main employer
was asked in every round, and, therefore, those variables also have no –2
codes.
For Panel 1 persons who have a current main job in Round 3
that continues from Round 1 or 2, the –2 code is not sufficient for those
variables that the person was skipped past at the time of the interview. This is
because the Panel 1 Round 1 and 2 data will not be included on this release and
therefore there are no data to which to refer. For such persons, the values for
the variables for these skipped questions are copied from the Round 1 or 2
constructed variable, depending on the round in which the job first became the
current main job. The accompanying variable RNDFLG31 indicates the round in
which these data were collected. For example, if the person has a Round 3
current main job that continues from Round 2 and was first reported as the
current main job in Round 2, HRWG31X will be a copy of the HRWAG2X from the 1996
Full Year Public Use Release and RNDFLG31 will be ‘2’, indicating the round
in which the job was first reported as the current main
job. Return To Table Of Contents
Employment Status (EMPST31, EMPST42, and EMPST53)
Employment status was asked for all persons aged 16 or older.
Allowable responses to the employment status question were as follows:
- "currently employed" if the person had a job at the interview
date;
- "has a job to return to" if the person did not work during the
reference period but had a job to return to as of the interview date;
- "employed during the reference period" if the person had no job
at the interview date but did work during the round;
- "not employed with no job to return to" if the person did not
have a job at the interview date, did not work during the reference period,
and did not have a job to return to.
These responses were mutually exclusive. A current main job
was defined for persons reporting that they were currently employed and
identified a current main job, and for persons who reported and identified a job
to return to. Therefore, job-specific information such as hourly wage exists for
persons not presently working at the interview date but who have a job to return
to as of the interview date. Return To Table Of Contents
Data Collection Round for Round 3/1 CMJ (RNDFLG31)
For Panel 1, if the Round 3 current main job (CMJ) is a
continuation CMJ from Round 2 or Round 1, the value of most "31"
variables will be copied forward from the variable representing the round in
which the job was first reported as the CMJ. For persons in Panel 1, RNDFLG31
indicates the round in which the Round 3 CMJ was first reported as the CMJ and
provides a timeframe for the reported wage information and other job details.
RNDFLG31 is used with many "31" variables to indicate the round on
which the reported information is based.
For persons in either panel, RNDFLG31 is set to inapplicable
(–1) for persons who are under age 16 or who do not have a CMJ in Panel 1
Round 3 or Panel 2 Round 1. For persons who are part of Panel 1, RNDFLG31 is
also set to inapplicable (–1) if person is out-of-scope in the 1997 portion of
Round 3. For persons who are part of Panel 2, RNDFLG31 is also set to
inapplicable (–1) if person is out-of-scope in Round 1. For persons who are
part of Panel 1, other values for RNDFLG31 are set as follows:
- 1 - for continuing Round 3 CMJs reported first in Round 1;
- 2 - for continuing Round 3 CMJs reported first in Round 2;
- 3 - for jobs newly reported as current main in Round 3;
- 9 - Round 3 CMJ is a continuation CMJ (wage information and other details
were not collected in Round 3) but the Round 2 CMJ record either does not
exist or is not the same job. This can occur in rare instances because
corrections made to a person’s record in a current file cannot be made to
that record in an earlier file due to data base processing constraints.
For persons who are part of Panel 2 and reported a Round 1
CMJ, RNDFLG31 equals "1" indicates that the job information
represented in the "31" variables was collected in Round 1. Return To Table Of Contents
Self-employed (SELFCM31, SELFCM42, and SELFCM53)
Information on whether an individual was self-employed at the
current main job was obtained for all persons who reported a current main job.
Certain questions, namely those regarding benefits and hourly wage, were not
asked of the self-employed. These variables indicate whether the establishment
reported by wage earners as the main source of employment offered the following
benefits:
- Paid leave to visit a doctor (PAYDR31, PAYDR42, and PAYDR53);
- Paid sick leave (SICPAY31, SICPAY42, and SICPAY53);
- Paid vacation (PAYVAC31, PAYVAC42, and PAYVAC53);
- Pension plan (RETPLN31, RETPLN42, and RETPLN53).
Those who were self-employed at their current main job are
coded as inapplicable (-1) for all these variables. Additionally, information on
whether the firm has more than one establishment (MORE31, MORE42, and MORE53)
and whether the establishment is a private for-profit, nonprofit, or a
government entity (JOBORG31, JOBORG42, and JOBORG53) is not applicable for
self-employed persons. Conversely, the variables that measure whether a business
is incorporated, a proprietorship, or a partnership (BSNTY31, BSNTY42, and
BSBTY53) apply only to those who are self-employed at their current main job.
Hourly wage (HRWG31X, HRWG42X, HRWG53X)
Hourly wage was asked of all persons who reported a current
main job that was not self-employment (SELFCM). An hourly wage was imputed using
a weighted sequential hot-deck procedure for those identified as having a
current main job who were not self-employed and who did not know their wage, or
refused to report a wage. Hourly wage for persons for whom employment status was
not known was coded as not ascertained (-9). Additionally, wages were imputed
for wage earners reporting a wage range and not a specific value. For these
persons, values were imputed from donors within the reported range. All imputed
wages can be identified as such by three wage imputation flags (HRWGIM31,
HRWGIM42, HRWGIM53). Note that wages were imputed only for persons with a
positive person weight.
For reasons of confidentiality, the hourly wage variable was
top-coded. A value of –10 indicates that the hourly wage was greater than or
equal to $43.75. The hourly wage variables on this file (HRWG31X, HRWG42X,
HRWG53X) should be considered along with their accompanying variables--HRHOW31,
HRHOW42, and HRHOW53—which indicate how the respective round hourly wage was
constructed. Hourly wage could be derived, as applicable, from a large number of
source variables. In the simplest case, hourly wage was reported directly by the
respondent. For other persons, construction of the hourly wage was based upon
salary, the time period on which the salary was based, and the number of hours
worked per time period. If the number of hours worked per time period was not
available, a value of 40 hours per week was assumed, as identified in the HRHOW
variable. It should be noted that HRHOW and HRWGIM may differ. As mentioned
above, wage imputations were performed on persons with positive weights only,
while HRHOW will apply to persons with a zero person-level weight. Return To Table Of Contents
Health Insurance (HELD31X, HELD42X, HELD53X, OFFER31X, OFFER42X, OFFER53X,
CHOIC31, CHOIC42, CHOIC53, DISVW31X, DISVW31X, DISVW42X, DISVW53X)
There are several employment-related health insurance
measures included in this release: health insurance held from a current main job
(HELD31X, HELD42X, HELD53X), health insurance offered from a current main job
(OFFER31X, OFFER42X, OFFER53X), and whether the individual had a choice of
health plans to choose from at the current main job (CHOIC31, CHOIC42, CHOIC53).
The HELD and OFFER variables were logically edited using health insurance
information.
Several persons indicated that they held health insurance
through a current main job in the employment section and then denied this
coverage later in the interview in the health insurance section. Employment
section health insurance HELD variables were edited for consistency to match the
health insurance measures obtained in the health insurance section. To allow for
easy identification of these individuals, round-specific flag variables were
constructed (DISVW31X, DISVW42X, DISVW53X).
Responses in the employment section for health insurance held
were recoded to be consistent with the variables in the health insurance section
of the survey. Due to questionnaire skip patterns, the responses to health
insurance offered were affected by editing the HELD variable. For example, if a
person responded that health insurance was held from a current main job, the
question relating to whether health insurance was offered was skipped. For
persons who responded in the employment section that they held health insurance
coverage and then disavowed the coverage in the health insurance section, we
could not ascertain whether they were offered a policy. These individuals are
coded as –9 for the OFFER variables.
Finally, persons under age 16 as well as persons aged 16 and
older who did not hold a current main job or who were self-employed with no
employees were coded as inapplicable for the health insurance-related employment
variables. Return To Table Of Contents
Hours (HOUR31, HOUR42, HOUR53)
Hours worked per week is a combination of two MEPS employment
section measures. For salaried persons in Panel 1, the hours measure refers to
the hours per week on which the salary is based. For all others, the hours
measure refers to usual hours worked per week.
Number of Employees (NUMEMP31, NUMEMP42, NUMEMP53)
Due to confidentiality concerns, the variable indicating the
number of employees at the establishment has been top coded at 500 or more
employees. NUMEMP indicates the number of employees at the location of the
person’s current main job. For persons who reported a categorical size, we
report a median estimated size from donors within the reported range.
Other Employment Variables
Information about industry and occupation types for a person’s
current main job at the interview date is also contained in this release. Based
on verbatim text fields collected during the interview, industry and occupation
types were first coded by trained coders into the three-digit codes defined by
the Bureau of the Census for the 1990 Census. For confidentiality reasons, these
codes were then condensed. CIND31, CIND42, and CIND53 represent the condensed
industry codes for a person’s current main job at the interview date. COCCP31,
COCCP42 and COCCP53 represent the condensed occupation codes for a person’s
current main job at the interview date.
Information indicating whether a person belonged to a labor
union (UNION31, UNION42, and UNION53) and whether a person worked an irregular
work shift (SHFTWK31, SHFTWK42, and SHFTWK53) is also contained in this release.
In addition, there are three round specific variables, which show the usual
daily start time of the current main job (BGNWK31, BGNWK42, and BGNWK53). There
are also three measures of the usual daily ending time of the current main job
(ENDWK31, ENDWK42, and ENDWK53). The values for these variables are coded in
24-hour military time and reflect the hours that the respondent reported as the
usual starting and ending times. There is an additional allowable value of ‘95’
indicating respondents who reported that their usual start and end times varied.
The day, month, and year that the current main job started
for Rounds 3, 4, and 5 of Panel 1 and Rounds 1, 2, and 3 of Panel 2 are provided
on this release (STJBDD31, STJBMM31, STJBYY31, STJBDD42, STJBMM42, STJBYY42,
STJBDD53, STJBMM53, and STJBYY53).
There are two measures included in this release that relate
to a person’s work history over a lifetime. One indicates whether a person
ever retired from a job as of the Round 5 interview date for Panel 1 persons or
the Round 3 interview date for Panel 2 persons (EVRETIRE). The other indicates
whether a person ever worked for pay as of the Round 5 interview date for Panel
1 persons or the Round 3 interview date for Panel 2 persons (EVRWRK). The latter
was asked of everyone who indicated that they were not working as of the round
interview date. Therefore, anyone who indicated current employment or who had a
job during any of the previous or current rounds was skipped past the question
identifying whether the person every worked for pay. These individuals were
coded as inapplicable (-1). The ever retired question was asked of all persons
who ever reported a job and were 55 years or older as of the round interview
date. Since both of these variables are not round specific, there are no –2
codes. Return To Table Of Contents
This release contains variables indicating the main reason a
person did not work since the start of the reference period (NWK31, NWK42, and
NWK53). If a person was not employed at all the during the reference period (at
the interview date or at any time during the reference period) but was employed
some time prior to the reference period, the person was asked to choose from a
list the main reason he or she did not work during the reference period. The
inapplicable (-1) category for the NWK variables includes persons:
- who were employed during the reference period;
- who were not employed during the reference period and who were never
employed;
- who were out-of-scope the entire reference period;
- who were less than 16 years old.
A measure of whether an individual had more than one job on
the round interview date (MORJOB31, MORJOB42, and MORJOB53) is provided on this
release. In addition to those under 16 and those individuals who were out of
scope, the inapplicable category includes those who did not report having a
current main job. Because this is not a job-specific variable, there are no –2
codes.
This release contains variables indicating if a current main
job changed between the third and fourth rounds for Panel 1 persons or between
the first and second rounds for Panel 2 persons (CHGJ3142) and between the
fourth and fifth rounds for Panel 1 persons or between the second and third
rounds for Panel 2 persons (CHGJ4253). In addition to the inapplicable, refused,
don’t know, and not ascertained categories, the change job variables were
coded to represent the following:
- 1 – person left previous round current main job and now has a new
current main job;
- 2 – person still working at the previous round’s current main job but,
as of the new round, no longer considers this job to be the current main job
and defines a new main job (previous round’s current main job is now a
current miscellaneous job);
- 3 – person left previous round’s current main job and does not have a
new job;
- 4 – person did not change current main job.
Finally, this release contains the reason given by the
respondent for the job change (YCHJ3142 and YCHJ4253). The reasons for a job
change were listed in the CAPI questionnaire and a respondent was asked to
choose the main reason from this list. In addition to those out of scope, those
under 16, and those not having a current main job, the inapplicable category for
YCHJ3142 and YCHJ4253 includes workers who did not change jobs. Return To Table Of Contents
2.5.7 Health Insurance Variables
Constructed and edited variables are provided that indicate
any coverage in each month of 1997 for the sources of health insurance coverage
collected during the MEPS interviews (Panel 1, Rounds 3 through 5 and Panel 2,
Rounds 1 through 3). In Rounds 2, 3, 4, and 5, insurance that was in effect at
the previous round’s interview date was reviewed with the respondent. Most of
the insurance variables have been logically edited to address issues that arose
during such reviews in Rounds 2, 3, 4, and 5. One edit to the private insurance
variables corrects for a problem concerning covered benefits which occurred when
respondents reported a change in any of their private health insurance plan
name. Additional edits address issues of missing data on the time period of
coverage for both public and private coverage that was either reviewed or
initially reported in a given round. For CHAMPUS/CHAMPVA coverage, respondents
who were classified as active duty military or who were over age 65 had their
reported CHAMPUS/CHAMPVA coverage overturned. Additional edits, described below,
were performed on the Medicare and Medicaid variables to assign persons to
coverage from these sources. Observations that contain edits assigning persons
to Medicare or Medicaid coverage can be identified by comparing the edited and
unedited versions of the Medicare and Medicaid variables.
Public sources include Medicare, CHAMPUS/CHAMPVA, Medicaid
and other public hospital/physician coverage. State-specific program
participation in non-comprehensive coverage (STAJA97-STADE97) was also
identified but is not considered health insurance for the purpose of this
survey. Return To Table Of Contents
Medicare
Medicare (MCRJA97-MCRDE97) coverage was edited
(MCRJA97X-MCRDE97X) for persons age 65 or over. Within this age group,
individuals were assigned Medicare coverage if:
They answered yes to a follow-up question on whether or
not they received Social Security benefits; or
They were covered by Medicaid, other public
hospital/physician coverage or Medigap coverage; or
Their spouse was age 65 or over and covered by Medicare; or
They reported CHAMPUS/CHAMPVA coverage.
Medicaid and Other Public Hospital/Physician Coverage
Questions about other public hospital/physician coverage were
asked in an attempt to identify Medicaid recipients who may not have recognized
their coverage as Medicaid. These questions were asked only if a respondent did
not report Medicaid directly. Respondents reporting other public
hospital/physician coverage were asked follow-up questions to determine if their
coverage was through a specific Medicaid HMO or if it included some other
managed care characteristics. Respondents who identified managed care from
either path were asked if they paid anything for the coverage and/or if a
government source paid for the coverage.
The Medicaid variables (MCDJA97-MCDDE97) have been edited
(MCDJA97X-MCDDE97X) to include persons who paid nothing for their other public
hospital/physician insurance when such coverage was through a Medicaid HMO or
reported to include some other managed care characteristics. In addition, a
small number of persons reporting AFDC or SSI coverage (questions included in
the MEPS health insurance sections for this purpose) were assigned Medicaid
coverage.
To assist users in further editing sources of insurance, this
file contains variables constructed from the other public hospital/physician
series that measure whether:
the respondent reported some type of managed care and
paid something for the coverage, Other Public A Insurance (OPAJA97-OPADE97);
and
the respondent did not report any managed care, Other
Public B Insurance (OPBJA97-OPBDE97).
The variables OPAJA97-OPADE97 and OPBJA97-OPBDE97 are
provided only to assist in editing and should not be used to make separate
insurance estimates for these types of insurance categories. Return To Table Of Contents
Any Public Insurance in Month
The file also includes summary measures that indicate whether
or not a sample person has any public insurance in a month (PUBJA97X-PUBDE97X).
Persons identified as covered by public insurance are those reporting coverage
under CHAMPUS/CHAMPVA, Medicare, Medicaid or other public hospital/physician
programs. Persons covered only by state-specific programs that did not provide
comprehensive coverage (STAJA97-STADE97), for example, Maryland Kidney Disease
Program, were not considered to have public coverage when constructing the
variables PUBJA97X-PUBDE97X.
Private Insurance
Variables identifying private insurance in general
(PRIJA97-PRIDE97) and specific private insurance sources [such as employer/union
group insurance (PEGJA97-PEGDE97); non-group (PNGJA97-PNGDE97); and other group
(POGJA97-POGDE97)] were constructed. Private insurance sources identify coverage
in effect at any time during each month of 1997. Separate variables identify
covered persons and policyholders (policyholder variables begin with the letter
"H"). These variables indicate coverage or policyholder status within
a source and do not distinguish between persons who are covered or are
policyholders on one or more than one policy within a given source. In some
cases, the policyholder was unable to characterize the source of insurance
(PDKJA97-PDKDE97). Covered persons (but not policyholders) are identified when
the policyholder is living outside the RU (POUJA97-POUDE97). An individual was
considered to have private health insurance coverage if, at a minimum, that
coverage provided benefits for hospital and physician services (including
Medigap coverage). Sources of insurance with missing information regarding the
type of coverage were assumed to contain hospital/physician coverage. Persons
without private hospital/physician insurance were not counted as privately
insured.
Health insurance through a job or union (PEGJA97-PEGDE97,
PRSJA97-PRSDE97) was initially asked about in the Employment Section of the
interview and later confirmed in the Health Insurance Section. Respondents also
had an opportunity to report employer and union group insurance
(PEGJA97-PEGDE97) for the first time in the Health Insurance Section, but this
insurance was not linked to a specific job.
All insurance reported to be through a job classified as
self-employed with firm size of 1 (PRSJA97-PRSDE97) was initially reported in
the Employment Section and verified in the Health Insurance Section. Unlike the
other employment-related variables (PEGJA97-PEGDE97), self-employed-firm size 1
(PRSJA97-PRSDE97) health insurance could not be reported in the Health Insurance
section for the first time. The variables PRSJA97-PRSDE97 have been constructed
to allow users to determine if the insurance should be considered
employment-related.
Private insurance that was not employment-related
(POGJA97-POGDE97, PNGJA97-PNGDE97, PDKJA97-PDKDE97 and POUJA97-POUDE97) was
reported in the Health Insurance Section only. Return To Table Of Contents
Any Insurance in Month
The file also includes summary measures that indicate whether
or not a sample person has any insurance in a month (INSJA97X-INSDE97X). Persons
identified as insured are those reporting coverage under CHAMPUS/CHAMPVA,
Medicare, Medicaid or other public hospital/physician or private
hospital/physician insurance (including Medigap plans). A person is considered
uninsured if not covered by one of these insurance sources.
Persons covered only by state-specific programs that provide
non-comprehensive coverage (STAJA97-STADE97), for example, Maryland Kidney
Disease Program, and those without hospital/physician benefits (for example,
private insurance for dental or vision care only, accidents or specific
diseases) were not considered to be insured when constructing the variables
INSJA97X-INSDE97X.
1997 Summary Insurance Coverage Indicators (PRVEV97 - INSCOV97)
The variables PRVEV97-UNINS97 summarize health insurance coverage for the
person in 1997 for the following types of insurance: private (PRVEV97);
CHAMPUS/CHAMPVA (CHPEV97); Medicaid (MCDEV97); Medicare (MCREV97); other public
A (OPAEV97); other public B (OPBEV97). Each variable was constructed based on
the values of the corresponding 12 month to month health insurance variables
described above. A value of 1 indicates that the person was covered for at least
one day of at least one month during 1997. A value of 2 indicates that the
person was not covered for a given type of insurance for all of 1997. The
variable UNINS97 summarizes PRVEV97-OPBEV97. Where PRVEV97-OPBEV97 are all equal
to 2, then UNINS97 equals 1; person was uninsured for all of 1997. Otherwise
UNINS97 is set to 2, not uninsured for some portion of 1997.
For user convenience this file contains a constructed variable INSCOV97 that
summarizes health insurance coverage for the person in 1997, with the following
3 values:
1 = ANY PRIVATE ( Person had any private insurance coverage (including
Champus/VA) any time during 1997)
2 = PUBLIC ONLY (Person had only public insurance coverage during
1997)
3 = UNINSURED ( Person was uninsured during all of 1997)
Please note this variable categorizes Champus as private coverage. If an
analyst wishes to consider Champus public coverage, the variable can easily be
reconstructed using the PRVEV97 and CHMPEV97 variables. Return To Table Of Contents
2.5.8 Health Status Variables
This data release incorporates information from calendar year 1997. However,
health status data obtained in Round 3 of Panel 2 are also included in variables
that have names ending in "53". Panel 2 Round 3 extended into 1998.
Therefore, for variables that have names ending in "53", some
information from early 1998 is included.
Health status variables in this data release can be classified into several
conceptually distinct sets:
1) Perceived health status and ADL and IADL limitations
2) Functional limitations and activity limitations
3) Vision problems
4) Hearing problems
5) Children’s health status
Variables in the first set were measured in all Rounds. Variables in
set 2 were measured in Rounds 3 and 5 for Panel 1 and Rounds 1 and 3 for Panel
2. Variables in sets 3, 4, and 5 were measured only in Round 4 for Panel 1 and
Round 2 for Panel 2.
In general, Health Status variables involved the construction of person-level
variables based on information collected in the Condition Enumeration and Health
Status sections of the questionnaire. Many Health Status questions were
initially asked at the family level to ascertain if anyone in the household had
a particular problem or limitation. These were followed up with questions to
determine which household member had each problem or limitation. All
information ascertained at the family level has been brought to the person level
for this file. Logical edits were performed in constructing the person-level
variables to assure that family-level and person-level values were consistent.
Particular attention was given to cases where missing values were reported at
the family level, to ensure that appropriate information was carried to the
person level.
Inapplicable cases occurred when a question was never asked because of a skip
pattern in the survey (e.g., individuals who were 13 years of age or older were
not asked some follow-up verification questions; individuals older than 17 were
not asked questions pertaining to children’s health status). Inapplicable
cases are coded as -1. In addition, deceased persons were coded as inapplicable
and received a code of -1.
Each of the sets of variables listed above will be described in turn. Return To Table Of Contents
2.5.8.1 Perceived Health Status and ADL and IADL Limitations
Perceived Health Status. Perceived health status (RTHLTH31, RTHLTH42, and
RTHLTH53) and perceived mental health status (MNHLTH31, MNHLTH42, and
MNHLTH53) were collected in the Condition Enumeration section. These questions
(CE01 and CE02) asked the respondent to rate each person in the family according
to the following categories: excellent, very good, good, fair, and poor. The
corresponding dichotomous variables RTPROX31, RTPROX42, RTPROX53, MNPROX31,
MNPROX42, and MNPROX53 each indicate whether the ratings of physical and
mental health were provided by oneself or by someone else.
IADL Help. The Instrumental Activities of Daily Living (IADL) Help or
Supervision variables (IADLHP31, IADLHP42, and IADLHP53) were each
constructed from a series of three questions administered in the Health Status
section of the interview. The initial question (HE01) determined if anyone in
the family received help or supervision with IADLs such as using the telephone,
paying bills, taking medications, preparing light meals, doing laundry, or going
shopping. If the response was "yes," a follow-up question (HE02) was
asked to determine which household member received this help or supervision. For
persons under age 13, a final verification question (HE03) was asked to confirm
that the IADL help or supervision was the result of an impairment or physical or
mental health problem. If the response to the final verification question was
"no," IADLHP31, IADLHP42, and IADLHP53 were coded
"no" for persons under the age of 13.
If no one in the family was identified as receiving help or supervision with
IADLs, all members of the family were coded as receiving no IADL help or
supervision. In cases where the response to the family-level question was
"refused" (-7), "don’t know" (-8), or not ascertained
(-9), all persons were coded according to the family-level response. In cases
where the response to the family-level question (HE01) was "yes" but
no specific individuals were identified in the follow-up question as having IADL
difficulties, all persons were coded as "don’t know" (-8).
ADL Help. The Activities of Daily Living (ADL) Help or Supervision
variable (ADLHLP31, ADLHLP42, and ADLHLP53) were each constructed in the
same manner as the IADL help variables, but using questions HE04-HE06. Coding
conventions for missing data were the same as for the IADL variables. Return To Table Of Contents
2.5.8.2 Functional and Activity Limitations
Functional Limitations. A series of questions pertained to functional
limitations, defined as difficulty in performing certain specific physical
actions. WLKLIM31 and WLKLIM53 were the filter questions, depending on the
Round. These variables were derived from a question (HE09) that was asked at the
family level: "Does anyone in the family have difficulties walking,
climbing stairs, grasping objects, reaching overhead, lifting, bending or
stooping, or standing for long periods of time?" If the answer was
"no" then all family members were coded as "no" (2) on
WLKLIM31 or WLKLIM53. If the answer was "yes," then the
specific persons who had any of these difficulties were identified and coded as
"yes" (1), and remaining family members were coded as "no".
If the response to the family-level question was "don’t know" (-8),
"refused" (-7), "missing" (-9), or "inapplicable"
(-1), then the corresponding missing value code was applied to each family
member’s value for WLKLIM31 or WLKLIM53. If the answer to HE09 was
"yes," but no specific individual was named as experiencing such
difficulties, then each family member was assigned -8. Deceased respondents were
assigned a -1 code ("inapplicable") for WLKLIM31 or WLKLIM53.
For Round 3 (Panel 1) and Round 1 (Panel 2), if any family member was coded
"yes" to WLKLIM31 a subsequent series of questions was administered.
The series of questions for which WLKLIM31 served as a filter was as follows:
LFTDIF31 - difficulty lifting 10 pounds
STPDIF31 - difficulty walking up 10 steps
WLKDIF31 - difficulty walking 3 blocks
MILDIF31 - difficulty walking a mile
STNDIF31 - difficulty standing 20 minutes
BENDIF31 - difficulty bending or stooping
RCHDIF31 - difficulty reaching over head
FNGRDF31 - difficulty using fingers to grasp
The series of questions was asked separately for each person who was coded
"yes" to WLKLIM31. The series of questions was not asked for other
individual family members for whom WLKLIM31 was "no." In addition,
this series was not asked about family members who were less than 13 years of
age, regardless of their status on WLKLIM31. Finally, these questions were not
asked about deceased family members. In such cases (i.e., WLKLIM31 = 2, or age
< 13, or PSTATS31 = 31), each question in the series was coded as
"inapplicable" (-1). Finally, if responses to WLKLIM31 were
"refused" (-7), "don’t know" (-8), "not
ascertained" (-9), or otherwise inapplicable (-1), then each question in
this series was coded as "inapplicable" (-1).
Analysts should note that, for WLKLIM31, there was no minimum age criterion
that was used to determine a skip pattern, whereas, for the subsequent series of
questions, persons less than 13 years old were skipped and coded as
"inapplicable". Therefore, it is possible for someone aged 12 or less
to have a code of 1 ("yes") on WLKLIM31, and also to have codes of
"inapplicable" on the subsequent series of questions.
For Round 5 (Panel 1) and Round 3 (Panel 2), the corresponding filter
question was WLKLIM53. The series of questions for which WLKLIM53 served as a
filter was as follows:
LFTDIF53 - difficulty lifting 10 pounds
STPDIF53 - difficulty walking up 10 steps
WLKDIF53 - difficulty walking 3 blocks
MILDIF53 - difficulty walking a mile
STNDIF53 - difficulty standing 20 minutes
BENDIF53 - difficulty bending or stooping
RCHDIF53 - difficulty reaching over head
FNGRDF53 - difficulty using fingers to grasp
Editing conventions were the same for this set of variables as they were for
the corresponding set described above. Return To Table Of Contents
Use of Assistive Technology and Social/Recreational Limitations
. The
variables indicating use of assistive technology (AIDHLP31 and AIDHLP53, from
question HE07) and social/recreational limitations (SOCLIM31 and
SOCLIM53, from question HE22) were collected initially at the family level. If
there was a "yes" response to the family-level question, a second
question identified which specific individual(s) the "yes" response
pertained to. Each individual identified as having the difficulty was coded
"yes" on the appropriate variable; all remaining family members were
coded "no." If the family-level response was "don’t know"
(-7), "refused" (-8), or not ascertained (-9), all persons were coded
with the family-level response. In cases where the family-level response was
"yes" but no specific individual was identified as having difficulty,
all family members were coded as "don’t know" (-8).
Work, Housework, and School Limitations . The variables indicating any
limitation in work, housework, or school (ACTLIM31 and ACTLIM53) were
constructed using questions HE19-HE20. Specifically, information was collected
initially at the family level. If there was a "yes" response to the
family-level question (HE19), a second question (HE20) identified which specific
individual(s) the "yes" response pertained to. Each individual
identified as having a limitation was coded "yes"; all remaining
family members were coded "no." If the family-level response was
"don’t know"(-7), "refused" (-8), or not ascertained (-9),
all persons were coded with the family-level response. In cases where the
family-level response was "yes" but no specific individual was
identified as having difficulty, all family members were coded as "don’t
know" (-8). Persons less than five years old were coded as inapplicable
(-1) on ACTLIM31 and ACTLIM53.
For Round 3 (Panel 1) or Round 1 (Panel 2) if ACTLIM31 was "yes"
and the person was 5 years of age or older, a follow-up question (HE20A) was
asked to identify the specific limitation or limitations for each person. These
included working at a job (WRKLIM31), doing housework (HSELIM31), or going to
school (SCHLIM31). Respondents could answer "yes" to each activity;
one person could thus report limitation in multiple activities. WRKLIM31,
HSELIM31, and SCHLIM31 have values of "yes" or "no" only if
ACTLIM31 was "yes;" each variable was coded as inapplicable (-1) if
ACTLIM31 was "no," "refused" (-7), or not ascertained (-9).
When ACTLIM31 was "don’t know" (-8), these variables were all coded
as "don’t know" (-8). If a person was under 5 years old or was
deceased, WRKLIM31, HSELIM31, and SCHLIM31 were each coded as
"inapplicable" (-1).
A second question (UNABLE31) asked if the person was completely unable to
work at a job, do housework, or go to school. This question was asked only of
the same set of respondents who provided data on WRKLIM31, HSELIM31, and
SCHLIM31. Therefore, those respondents who were coded "no" on
ACTLIM31, or were under 5 years of age, or were deceased, were coded as
inapplicable (-1) on UNABLE31. UNABLE31 was asked once for whichever set of
WRKLIM31, HSELIM31, and SCHLIM31 the respondent had limitations; if a respondent
was limited in more than one of these three activities, UNABLE31 did not
specify if the respondent was completely unable to perform all of them, or only
some of them.
For Rounds 5 (Panel 1) and 3 (Panel 2) corresponding variables were ACTLIM53,
WRKLIM53, HSELIM53, SCHLIM53, and UNABLE53. Editing conventions were the same as
those described above.
Cognitive Limitations . The variables indicating any cognitive limitation
(COGLIM31 or COGLIM53, depending on the round) were collected at the family
level as a three-part question (HE24-01 to HE24-03) indicating if any of the
adults in the family (1) experience confusion or memory loss, (2) have problems
making decisions, or (3) require supervision for their own safety. If a
"yes" response was obtained to any item, the persons affected were
identified in HE25 and COGLIM31 was coded as "yes." Remaining family
members not identified were coded as "no" for COGLIM31.
If responses to HE24-01 though HE24-03 were all "no," or if two of
three were "no" and the remaining was "don’t know,"
"refused," or not ascertained, all family members were coded as
"no." If responses to the three questions were combinations of
"don’t know," "refused," and missing, all persons were
coded as "don’t know" (-8). If the response to any of the three
questions was "yes" but no individual was identified in HE25, all
persons were coded as "don’t know" (-8).
Analogous editing specifications were implemented for COGLIM53.
The cognitive limitations variables (COGLIM31 or COGLIM53) reflect
whether any of the three component questions is "yes."
Respondents with one, two, or three specific cognitive limitations cannot be
distinguished. In addition, because the question asked specifically about adult
family members, all persons less than 18 years of age are coded as inapplicable
(-1) on this question. Return To Table Of Contents
2.5.8.3 Vision Problems
A series of questions (HE26 to HE32) provides information on visual
impairment. These questions were asked of all household members, regardless of
age. Deceased respondents were coded as not applicable (-1).
WRGLAS42 indicates whether a person wears eyeglasses or contact lenses. This
variable was based on two questions, HE26 and HE27. The initial question (HE26)
determined if anyone in the family wore eyeglasses or contact lenses. If the
response was "yes," a follow-up question (HE27) was asked to determine
which household member(s) wore eyeglasses or contact lenses. If the family-level
response was "don’t know"(-8), "refused" (-7), or not
ascertained (-9), all persons were coded with the family-level response. In
cases where the family-level response was "yes" but no specific
individual was identified as wearing glasses or contact lenses, all family
members were coded as "don’t know" (-8).
SEEDIF42 indicates whether anyone in the family had difficulty seeing (with
glasses or contacts, if used). This variable was based on two questions, HE28
and HE29. The initial question (HE28) determined if anyone in the family had
difficulty seeing. If the response was "yes," a follow-up question
(HE29) was asked to determine which household member(s) had a visual impairment.
If the family-level response was "don’t know"(-8),
"refused" (-7), or not ascertained (-9), all persons were coded with
the family-level response. In cases where the family-level response was
"yes" but no specific individual was identified as having difficulty
seeing, all family members were coded as "don’t know" (-8).
Three subsequent questions were asked only for individuals who had difficulty
seeing (i.e., SEEDIF42 = 1). Persons with no visual impairment were coded as not
applicable (-1) for these questions, as were persons with don’t know (-8),
refused (-7), or not ascertained (-9) responses to SEEDIF42. BLIND42 determined
if a person with difficulty seeing was blind. For persons who were not blind
(BLIND42 = 2), READNW42 asked whether the person could see well enough to read
ordinary newspaper print (with glasses or contacts, if used); persons who were
blind were not asked this question and were coded as not applicable (-1). For
persons who could not read ordinary newspaper print (READNW42 = 2), RECPEP42
asked if the person could see well enough to recognize familiar people standing
two or three feet away. Persons who were blind or who could read newsprint were
not asked this question and were coded as not applicable (-1).
VISION42 summarizes the pattern of responses to the set of visual impairment
questions. Codes for VISION42 are as follows:
- - No difficulty seeing (SEEDIF42 = 2)
- - Some difficulty seeing, can read newsprint (SEEDIF42 = 1 and READNW42
= 1)
- - Some difficulty seeing, can not read newsprint, can recognize
familiar people (SEEDIF42 = 1 and READNW42 = 2 and RECPEP42 = 1)
- - Some difficulty seeing, can not read newsprint, can not recognize
familiar people but is not blind (SEEDIF42 =1 and READNW42 = 2 and RECPEP42
= 2)
- - Blind (SEEDIF42 = 1 and BLIND42 = 1).
Return To Table Of Contents
2.5.8.4 Hearing Problems
A series of questions (HE33 to HE39) provides information on hearing
impairment. These questions were asked of all household members, regardless of
age. Deceased respondents were coded as not applicable (-1).
HEARAD42 indicates whether a person wears a hearing aid. This variable was
based on two questions, HE33 and HE34. The initial question (HE33) determined if
anyone in the family wore a hearing aid. If the response was "yes," a
follow-up question (HE34) was asked to determine which household member(s) wore
a hearing aid. If the family-level response was "don’t know"(-8),
"refused" (-7), or not ascertained (-9), all persons were coded with
the family-level response. In cases where the family-level response was
"yes" but no specific individual was identified as wearing a hearing
aid, all family members were coded as "don’t know" (-8).
HEARDI42 indicates whether anyone in the family had difficulty hearing (with
a hearing aid, if used). This variable is based on two questions, HE35 and HE36.
The initial question (HE35) determined if anyone in the family had difficulty
hearing. If the response was "yes," a follow-up question (HE36) was
asked to determine which household member had an aural impairment. If the
family-level response was "don’t know"(-8), "refused"
(-7), or not ascertained (-9), all persons were coded with the family-level
response. In cases where the family-level response was "yes" but no
specific individual was identified as using a hearing aid, all family members
were coded as "don’t know" (-8).
Three subsequent questions were asked only for individuals who had difficulty
hearing (i.e., HEARDI42 = 1). Persons with no hearing impairment were coded as
inapplicable (-1) for these questions, as were persons with don’t know (-8),
refused (-7), or not ascertained (-9) responses to HEARDI42. DEAF42 determined
if a person with difficulty hearing was deaf. For persons who were not deaf
(DEAF42 = 2), HEARMO42 asked whether the person could hear well enough to hear
most of the things people say (with a hearing aid, if used); persons who were
deaf were not asked this question and were coded as not applicable (-1). For
persons who could not hear most things people say (HEARMO42 = 2), HEARSM42 asked
if the person could hear well enough to hear some of the things that people say.
Persons who were deaf or who could hear most conversation were not asked this
question and were coded as inapplicable (-1).
HEARNG42 summarizes the pattern of responses to the set of hearing impairment
questions. Codes for HEARNG42 are as follows:
1 - No difficulty hearing (HEARDI42 = 2)
2 - Some difficulty hearing, can hear most things people say
(HEARDI42 = 1 and HEARMO42 = 1)
3 - Some difficulty hearing, can not hear most things people say, can
hear some things people say (HEARDI42 = 1 and HEARMO42 = 2 and HEARSM42
= 1)
4 - Some difficulty hearing, can not hear most things people say, can
not hear some things people say, but not deaf (HEARDI42 =1 and HEARMO42
= 2 and HEARSM42 = 2)
5 - Deaf (HEARDI42 = 1 and DEAF42 = 1). Return To Table Of Contents
2.5.8.5 Any Limitation Rounds 3, 4, and 5 (Panel 1) / Rounds 1, 2, and 3 (Panel
2)
ANYLIM97 summarizes whether the respondent has any ADL, IADL, activity,
functional, or sensory limitations. This variable was derived based on data from
Rounds 3, 4, and 5 (Panel 1) or Rounds 1, 2, and 3 (Panel 2). ANYLIM97 was built
upon component variables IADLHP31, IADLHP42, IADLHP53, ADLHLP31, ADLHLP42,
ADLHLP53, WLKLIM31, WLKLIM53, ACTLIM31, ACTLIM53, SEEDIF42, and HEARDIF42. (The
latter two variables, discussed above, indicate any visual or hearing
impairment, respectively.) If any of these components was coded "yes",
then ANYLIM97 was coded "yes" (1). If all components equaled
"no", then ANYLIM97 equaled "no" (2). If all the components
had missing value codes (i.e., -7, -8, -9, or –1), then ANYLIM97 was coded as
not ascertained (-9). If some components were "no" and others had
missing value codes, ANYLIM97 was coded as not ascertained (-9). The exception
to this latter rule was for children less than five years old, who did not
receive the ACTLIM31 or ACTLIM53 questions; for these respondents, if all other
components were "no", then ANYLIM97 was coded as "no" (2).
The variable label for ANYLIM97 departs slightly from conventions. Typically,
variables that end in "97" refer only to 1997. However, because some
of the variables utilized to construct ANYLIM97 spanned 1997 and 1998, some
information from early 1998 is included in this variable.
Return To Table Of Contents
2.5.8.6 Children’s Health Status
Play Limitations (Children age 4 and under). The variable LIMACT42,
indicating limitation in activities for children ages 0 through 4, was
constructed using questions HE40 and HE41. The initial question (HE40)
determined if any child aged 4 or under in the family was limited in any way,
including play activity, because of an impairment or physical or mental health
problem. If the response was "yes," the follow-up question determined
which child should be coded "yes." If there were other children aged 4
or under in the family who were not identified as having limitations, they were
coded "no." If the answer to LIMACT42 was "no," all children
aged four or under in the family were coded "no." If there was an
indication that a child had a limitation, but no child was identified, all
children within the age category were coded "don’t know" (-8). In
cases where the response to the family-level question was "don’t
know" (-8), refused (-7), or not ascertained (-9), all children ages 4 and
under were coded according to the family-level response. If a person's age (as
measured by the Panel 1 Round 4/Panel 2 Round 2 age variable) was greater than
4, LIMACT42 was coded -1.
Other variables indicate if children aged 0 to 4 were limited in the kind or
amount of play activities (PLYLIM42), were unable to play (CANTPL42), or
participated in special programs or early interventions (SPCPRO42). If a person
aged 4 or under had no activity limitations (i.e., LIMACT42 = 2), then PLYLIM42,
CANTPL42, and SPCPRO42 were each coded -1. If a person's age (as measured by the
Panel 1 Round 4/Panel 2 Round 2 age variable) was greater than 4, PLYLIM42,
CANTPL42, and SPCPRO42 were coded -1.
Immunization Variables (Children ages 0 through 6). Immunization
information was collected at the person level for children ages 0 through 6 by
questions HE45 to HE49A. If age of child, as measured by the Panel 1 Round
4/Panel 2 Round 2 age variable, was greater than 6, all immunization variables
were coded -1. For questions about diphtheria, whooping cough and tetanus (DPT)
or polio immunization (DPTSHT42, POLSHT42), there were follow up questions that
asked about the frequency of the immunization shots or drops (NUMDPT42,
NUMPOL42). If the answer to DPTSHT42 or POLSHT42 was "no," "don’t
know," or "refused," the respective follow-up variables NUMDPT42
and NUMPOL42 were coded -1. For questions about immunization for
measles/mumps/rubella (MMRSHT42) and for hepatitis (HEPSHT42), there were no
follow-up questions. Return To Table Of Contents
Behavioral Problem Variables (Children ages 5 to 17) The series of
questions HE50_01 to HE50_13 inquired about possible child behavioral problems.
Variables in this set include:
MOMPRO42: problem getting along with mother
DADPRO42: problem getting along with father
UNHAP42: feeling unhappy or sad
SCHLBH42: problem with behavior at school
HAVFUN42: problem having fun
ADUPRO42: problem getting along with adults
NERVAF42: problem with child feeling nervous or afraid
SIBPRO42: problem getting along with siblings
KIDPRO42: problem getting along with other kids
SPRPRO42: problem engaging in sports or hobbies
SCHPRO42: problem doing schoolwork
HOMEBH42: problem with behavior at home
TRBLE42: problem staying out of trouble.
If the age of the child (as measured by the Panel 1 Round 4/Panel 2 Round 2
age variable) was less than 5 or greater than 17, the variables MOMPRO42 to
TRBLE42 were coded -1.
Certain questions in this series could be inapplicable for a specific child.
For example, if a child’s mother was deceased, a question about how a child
gets along with his/her mother is inapplicable. Similarly, the question about
problems getting along with siblings would be inapplicable for only children. In
such instances, the relevant variable was coded 99 to indicate that it was
inapplicable. Return To Table Of Contents
Special Education and Special Services (Children ages 5-17).
A series of
questions asked about participation in special education programs or receipt of
therapy or special services. If the respondent was not in the age range of 5-17
years of age (as measured by the Panel 1 Round 4/Panel 2 Round 2 age variable),
or if the respondent was deceased, these questions were coded as inapplicable
(-1).
SPCSCH42 is based on question HE51, which asked whether the child had an
impairment or a physical or mental health problem that limited school attendance
or required a special school program. This question served as a filter for
subsequent questions. If the response "no"(2), "refused"
(-7), or "don’t know" (-8), then SPECED42 through CANTSC42 were
coded as inapplicable (-1).
If the response to SPCSCH42 was "yes" (1) then question HE52
(SPECED42) was asked. SPECED42 asked whether the child was enrolled in any type
of special education or received related services. Possible responses to this
question were "yes, enrolled in special education" (1), "yes,
enrolled in related services," (2), "yes, both special education and
special services," (3), "no" (4), and "other"(91).
If responses to SPECED42 were coded as 2 or 3, then respondents were
presented with a list of other related services and asked to indicate which
one(s) the child had received. Respondents could indicate more than one type of
service. These questions constitute variables SPCHTH42 to OTHSVC42.
SPCHTH42: Received speech therapy
OCUPTH42: Received occupational therapy
VOCSVC42: Received vocational services
TUTOR42: Received tutoring
READIN42: Uses a reader or interpreter
PHYTHR42: Received physical therapy
LIFSKL42: Received life skills training
PSYCNS42: Received psychological counseling
FAMCNS42: Received family counseling
RECTH4R2: Received recreational therapy
OTHSVC42: Received other school services
Responses to these questions were coded as inapplicable (-1) if the response
to SPECED42 was 1 (enrolled in special education only), or -7 (refused), or -8
(don’t know).
If the response to SPCSCH42 was "yes"(1) then question HE53
(CANTSC42) was asked. This question asked whether the child was limited in
attendance or unable to attend school due to an impairment or a physical or
mental health problem. Responses of "limited in attendance" were coded
1, "unable to attend" as 2, and "neither" as 3.
Question HE54 (LMOACT42) was asked of all children ages 5-17. This question
ascertained whether the child was limited in any way in activities other than
school because of an impairment or a physical or mental health problem.
Children’s Health Status: General Questions (ages 0 - 17)
Several questions were asked about all children ages 0 through 17.
Respondents who were older than 17 or who were deceased were coded as not
applicable (-1) for these variables. Three questions asked for ratings of the
child’s health on a 4-point Likert scale, ranging from "definitely
false"(1) to "definitely true"(4). These questions were:
HLTHY42: Child resists illness.
NTHLTH42: Child seems to be less healthy than other children.
GETSIC42: Child seems to catch diseases that are going around.
In addition, information was provided on each child’s height in feet
(HGTFT42) and inches (HGTIN42), as well as each child’s weight in pounds
(WGTLB42) and in ounces (WGTOZ42).
Finally, CHLIM42 was constructed to reflect each child’s inability to
perform age-appropriate social roles. For children aged 0 to 4, this variable
was based on responses to LIMACT42, PLYLIM42 and CANTPL42; for children aged
5-17, it was based on responses to SPCSCH42, CANTSC42 and LMOACT42. If any one
of these variables had a "yes" response (i.e., codes of 1 for
LIMACT42, PLYLIM42, CANTPL42, SPCSCH42, or LMOACT42, or codes of 1 or 2 for
CANTSC42), then CHLIM42 was coded as "yes"(1). If the relevant
variables were all "no", then CHLIM42 was coded as "no"(2).
CHLIM42 was coded as "not ascertained"(-9) if the relevant variables
were combinations of "refused"(-7), "don’t know"(-8), or
not ascertained (-9). Return To Table Of Contents
2.5.9 Utilization, Expenditures and Source of
Payment Variables (TOTTCH97-RXOSR97)
The MEPS Household Component (HC) collects data in each round on use and
expenditures for office and hospital-based care, home health care, dental
services, vision aids, and prescribed medicines. Data were collected for each
sample person at the event level (e.g. doctor visit, hospital stay) and summed
across rounds 1-3 (excluding 1997 events covered in round 3) to produce the
annual utilization and expenditure data for 1997 in this file. In addition, the
MEPS Medical Provider Component (MPC) is a follow-back survey that collected
data from a sample of medical providers and pharmacies that were used by sample
persons in 1997. Expenditure data collected in the MPC are generally regarded as
more accurate than information collected in the HC and were used to improve the
overall quality of MEPS expenditure data in this file (see below for description
of methodology used to develop expenditure data).
This file contains utilization and expenditure variables for several
categories of health care services. In general, there is one utilization
variable (based on HC responses only), 13 expenditure variables (derived from
both HC and MPC responses), and 1 charge variable for each category of health
care service. The utilization variable is typically a count of the number of
medical events reported for the category. The 13 expenditure variables consist
of an aggregate total payments variable, 10 main component source of payment
category variables, and 2 additional source of payment category variables (see
below for description of source of payment categories). Expenditure variables
for all categories of health care combined are also provided.
The table in Appendix 3 provides an overview of the utilization and
expenditure variables included in this file. For each health service category,
the table lists the corresponding utilization variable(s) and provides a general
key to the expenditure variable names (13 per service category). The first 3
characters of the expenditure variable names reflect the service category
(except only 2 characters for prescription medicines) while the subsequent 3 characters
(*** in table) reflect the naming convention for the source of payment
categories described below (except only 2 characters for Veterans
Administration). The last 2 positions of all utilization and expenditure
variable names reflect the survey year (i.e. 97). More details are provided on
the utilization and expenditure variables in sections 2.5.9.1 and 2.5.9.2 below.
Return To Table Of Contents
2.5.9.1 Expenditures Definition
Expenditures on this file refer to what is paid for health care services.
More specifically, expenditures in MEPS are defined as the sum of direct
payments for care provided during the year, including out-of-pocket payments and
payments by private insurance, Medicaid, Medicare, and other sources. Payments
for over the counter drugs and for alternative care services are not included in
MEPS total expenditures. Indirect payments not related to specific medical
events, such as Medicaid Disproportionate Share and Medicare Direct Medical
Education subsidies, are also not included.
The definition of expenditures used in MEPS is somewhat different from the
1987 NMES and 1977 NMCES surveys where Acharges@
rather than Asum of payments@
were used to measure expenditures. This change was adopted because charges
became a less appropriate proxy for medical expenditures during the 1990=s
due to the increasingly common practice of discounting charges. Another change
from the two prior surveys is that charges associated with uncollected
liability, bad debt, and charitable care (unless provided by a public clinic or
hospital) are not counted as expenditures because there are no payments
associated with those classifications.
While the concept of expenditures in MEPS has been operationalized as
payments for health care services, variables reflecting charges for services
received are also provided on the file (see below). Analysts should use caution
when working with the charge variables because they do not typically represent
actual dollars exchanged for services or the resource costs of those services. Return To Table Of Contents
Data Sources on Expenditures
The expenditure data included on this file were derived from the MEPS
Household and Medical Provider Components. Only HC data were collected for
nonphysician visits, dental and vision services, other medical equipment and
services, and home health care not provided by an agency while data on
expenditures for care provided by home health agencies were only collected in
the MPC. In addition to HC data, MPC data were collected for some office-based
visits to physicians (or medical providers supervised by physicians),
hospital-based events (e.g. inpatient stays, emergency room visits, and
outpatient department visits), and prescribed medicines. For these types of
events, MPC data were used if complete; otherwise HC data were used if complete.
Missing data for events where HC data were not complete and MPC data were not
collected or complete were derived through an imputation process (see below).
A series of logical edits were applied to both the HC and MPC data to correct
for several problems including outliers, copayments or charges reported as total
payments, and reimbursed amounts that were reported as out of pocket payments.
In addition, edits were implemented to correct for misclassifications between
Medicare and Medicaid and between Medicare HMO=s
and private HMO=s as payment sources.
Data were not edited to insure complete consistency between the health insurance
and source of payment variables on the file.
Imputation for Missing Expenditures and Data Adjustments
Expenditure data were imputed to 1) replace missing data, 2) provide
estimates for care delivered under capitated reimbursement arrangements, and 3)
to adjust household reported insurance payments because respondents were often
unaware that their insurer paid a discounted amount to the provider. This
section contains a general description of the approaches used for these three
situations. A more detailed description of the editing and imputation procedures
will be provided in the documentation for the forthcoming MEPS event level
files.
Missing data on expenditures were imputed using a weighted sequential
hot-deck procedure for most medical visits and services. In general, this
procedure imputes data from events with complete information to events with
missing information but similar characteristics. For each event type, selected
predictor variables with known values (e.g., total charge, demographic
characteristics, region, provider type, and characteristics of the event of
care, such as whether it involved surgery) were used to form groups of donor
events with known data on expenditures, as well as identical groups of recipient
events with missing data. Within such groups, data were assigned from donors to
recipients, taking into account the weights associated with the MEPS complex
survey design. Only MPC data were used as donors for hospital-based events while
data from both the HC and MPC were used as donors for office-based physician
visits. The general approach that was used to impute missing expenditure data on
prescribed medicines is described in section 2.5.9.2 below.
Because payments for medical care provided under capitated reimbursement
arrangements and through public clinics and Veterans=
Hospitals are not tied to particular medical events, expenditures for events
covered under those types of arrangements and settings were also imputed. Events
covered under capitated arrangements were imputed from events covered under
managed care arrangements that were paid based on a discounted fee-for-service
method, while imputations for visits to public clinics and Veterans=
Hospitals were based on similar events that were paid on a fee-for-service
basis. As for other events, selected predictor variables were used to form
groups of donor and recipient events for the imputations.
An adjustment was also applied to some HC reported expenditure data because
an evaluation of matched HC/MPC data showed that respondents who reported that
charges and payments were equal were often unaware that insurance payments for
the care had been based on a discounted charge. To compensate for this
systematic reporting error, a weighted sequential hot-deck imputation procedure
was implemented to determine an adjustment factor for HC reported insurance
payments when charges and payments were reported to be equal. As for the other
imputations, selected predictor variables were used to form groups of donor and
recipient events for the imputation process. Return To Table Of Contents
Methodology for Flat Fee Expenditures
Most of the expenditures for medical care reported by MEPS participants are
associated with single medical events. However, in some situations there is one
charge that covers multiple contacts between a medical provider and patient
(e.g. obstetrician services, orthodontia). In these situations (generally called
flat or global fees), total payments for the flat or global fee were included if
the initial service was provided in 1997. For example, all payments for an
orthodontist=s fee that covered
multiple visits over three years were included if the initial visit occurred in
1997. However, if a visit in 1997 to an orthodontist was part of a flat fee in
which the initial visit occurred in 1995, then none of the payments for the flat
fee were included.
The approach used to count expenditures for flat fees may create what appear
to be inconsistencies between utilization and expenditure variables. For
example, if several visits under a flat fee arrangement occurred in 1997 but the
first visit occurred in 1995, then none of the expenditures were included,
resulting in low expenditures relative to utilization for that person.
Conversely, the flat fee methodology may result in high expenditures for some
persons relative to their utilization. For example, all of the expenditures for
an expensive flat fee were included even if only the first visit covered by the
fee had occurred in 1997. On average, the methodology used for flat fees should
result in a balance between overestimation and underestimation of expenditures
in a particular year.
Zero Expenditures
There are some medical events reported by respondents where the payments were
zero. This could occur for several reasons including (1) free care was provided,
(2) bad debt was incurred, (3) care was covered under a flat fee arrangement
beginning in an earlier year, or (4) follow-up visits were provided without a
separate charge (e.g. after a surgical procedure). In summary, these types of
events have no impact on the person level expenditure variables contained in
this file. Return To Table Of Contents
Source of Payment Categories
In addition to total expenditures, variables are provided which itemize
expenditures according to the major source of payment categories. These
categories are:
- Out of pocket by user or family (SLF);
- Medicare (MCR);
- Medicaid (MCD);
- Private Insurance (PRV);
- Veterans’ Administration, excluding CHAMPVA (VA);
- CHAMPUS (i.e. TRICARE) or CHAMPVA (CHM);
- Other Federal Sources--includes Indian Health Service, Military
Treatment Facilities, and other care provided by the Federal government
(OFD);
- Other State and Local Source--includes community and neighborhood
clinics, State and local health departments, and State programs other than
Medicaid (STL);
- Worker=s Compensation (WCP);
- Other Unclassified Sources--includes sources such as automobile,
homeowner=s, liability, and
other miscellaneous or unknown sources (OSR).
Two additional source of payment variables were created to classify
payments for particular persons that appear inconsistent due to differences
between the survey questions on health insurance coverage and sources of
payment for medical events. These variables include:
- Other Private (OPR)Cany type
of private insurance payments reported for persons not reported to have
any private health insurance coverage during the year as defined in MEPS
(i.e. for hospital and physician services); and
- Other Public (OPU)CMedicaid
payments reported for persons who were not reported to be enrolled in the
Medicaid program at any time during the year.
Though relatively small in magnitude, users should exercise caution when
interpreting the expenditures associated with the OPR and OPU categories. While
these payments stem from apparent inconsistent responses to the health insurance
and source of payment questions in the survey, some of these inconsistencies may
have logical explanations. For example, private insurance coverage in MEPS is
defined as having a major medical plan covering hospital and physician services.
If a MEPS sample person did not have such coverage but had a single service type
insurance plan (e.g. dental insurance) that paid for a particular episode of
care, those payments may be classified as Aother
private@. Some of the Aother
public@ payments may stem from
confusion between Medicaid and other state and local programs or may be for
persons who were not enrolled in Medicaid, but were presumed eligible by a
provider who ultimately received payments from the program.
The naming conventions used for the source of payment expenditure variables
are shown in parentheses in the list of categories above and in the key to the
attached table in Appendix 3. In addition, total expenditure variables (EXP in
key) based on the sum of the 12 source of payment variables above are provided.
Charge Variables
In addition to the expenditure variables described above, a variable
reflecting total charges is provided for each type of service category (except
prescribed medicines). This variable represents the sum of all fully
established charges for care received and usually does not reflect actual
payments made for services, which can be substantially lower due to factors such
as negotiated discounts, bad debt, and free care (see above). The naming
convention used for the charge variables (TCH) is also included in the key to
the attached table in Appendix 3. The total charge variable across services
(TOTTCH97) excludes prescribed medicines. Return To Table Of Contents
2.5.9.2 Utilization and Expenditure Variables by
Type of Medical Service
The following sections summarize definitional, conceptual and analytic
considerations when using the utilization and expenditure variables in this
file. Separate discussions are provided for each MEPS medical service category.
Medical Provider Visits (i.e., Office-Based Visits)
Medical provider visits consist of encounters that took place primarily in
office-based settings and clinics. Care provided in other settings such as a
hospital, nursing home, or a person=s
home are not included in this category.
The total number of office based visits reported for 1997 (OBTOTV97) as well
as the number of such visits to physicians (OBDRV97) and nonphysician providers
(OBOTHV97) are contained in this file. For a small proportion of sample persons,
the sum of the physician and nonphysician visit variables (OBDRV97+OBOTHV97) is
less than the total number of office-based visits variable (OBTOTV97) because
OBTOTV97 contains reported visits where the respondent did not know the type of
provider.
Non-physician visits (OBOTHV97) include visits to the following types of
providers: chiropractors, midwives, nurses and nurse practitioners,
optometrists, podiatrists, physician=s
assistants, physical therapists, occupational therapists, psychologists, social
workers, technicians, receptionists/clerks/secretaries, or other medical
providers. Separate utilization variables are included for selected types of
more commonly seen non-physician providers including chiropractors (OBCHIR97),
nurses/nurse practitioners (OBNURS97), optometrists (OBOPTO97), physician
assistants (OBASST97), and physical or occupational therapists (OBTHER97).
Expenditure variables associated with all medical provider visits, physician
visits, and non-physician visits in office-based settings can be identified
using the attached table in Appendix 3. As for the corresponding utilization
variables, the sum of the physician and non-physician visit expenditure
variables (e.g. OBDEXP97+OBOEXP97) is less than the total office-based
expenditure variable (OBVEXP97) for a small proportion of sample persons. This
can occur because OBVEXP97 includes visits where the respondent did not know the
type of provider seen. Return To Table Of Contents
Hospital Events
Separate utilization variables for hospital care are provided for each type
of setting (inpatient, outpatient department, and emergency room) along with two
expense variables per setting; one for basic hospital facility expenses and
another for payments to physicians who billed separately for services provided
at the hospital. These payments are referred to as "separately billing
doctor" or SBD expenses.
Hospital facility expenses include all expenses for direct hospital care,
including room and board, diagnostic and laboratory work, x-rays, and similar
charges, as well as any physician services included in the hospital charge.
Separately billing doctor (SBD) expenses typically cover services provided to
patients in hospital settings by providers like radiologists, anesthesiologists,
and pathologists, whose charges are often not included in hospital bills.
Hospital Outpatient Visits
Variables for the total number of reported visits to hospital outpatient
departments in 1997 (OPTOTV97) as well as the number of outpatient department
visits to physicians (OPDRV97) and non-physician providers (OPOTHV97) are
contained in this file. For a small proportion of sample persons, the sum of the
physician and non-physician visit variables (OPDRV97+OPOTHV97) is less than the
total number of outpatient visits variable (OPTOTV97) because OPTOTV97 contains
reported visits where the respondent did not provide information on the type of
provider seen.
Expenditure variables (both facility and SBD) associated with all medical
provider visits, physician visits, and non-physician visits in outpatient
departments can be identified using the attached table in Appendix 3. As for the
corresponding utilization variables, the sum of the physician and non-physician
expenditure variables (e.g. OPVEXP97+OPOEXP97 for facility expenses) is less
than the variable for total outpatient department expenditures (OPFEXP97) for a
small proportion of sample persons. This can occur because OPFEXP97 includes
visits where the respondent did not know the type of provider seen. No
expenditure variables are provided for health care consultations that occurred
over the telephone.
Hospital Emergency Room Visits
The variable ERTOT97 represents a count of all emergency room visits reported
for the survey year. Expenditure variables associated with ERTOT97 are
identified in the attached table in Appendix 3. It should be noted that
hospitals usually include expenses associated with emergency room visits that
immediately result in an inpatient stay with the charges and payments for the
inpatient stay. Therefore, to avoid the potential for double counting when
imputing missing expenses, separately reported expenditures for emergency room
visits that were identified in the MPC as directly linked to an inpatient stay
were included as part of the inpatient stay only (see below). This strategy to
avoid double counting resulted in $0 expenditures for these emergency room
visits. However, these $0 emergency room visits are still counted as separate
visits in the utilization variable ERTOT97. Return To Table Of Contents
Hospital Inpatient Stays
Two measures of total inpatient utilization are provided on the file: (1)
total number of hospital discharges (IPDIS97) and (2) the total number of nights
associated with these discharges (IPNGTD97). IPDIS97 includes hospital stays
where the dates of admission and discharge were reported as identical. These
"zero night stays" can be included or excluded from inpatient analyses
at the user=s discretion (see last
paragraph of this section). If the number of nights in the hospital could not be
computed for any reported stay for a person, then IPNGTD97 was assigned a
missing value.
Expenditure variables associated with hospital inpatient stays are identified
in the attached table in Appendix 3. To the extent possible, payments associated
with emergency room visits that immediately preceded an inpatient stay are
included with the inpatient expenditures (see above) and payments associated
with healthy newborns are included with expenditures for the mother (see next
paragraph for more detail).
Data used to construct the inpatient utilization and expenditure variables
for newborns were edited to exclude stays where the newborn left the hospital on
the same day as the mother. This edit was applied because discharges for infants
without complications after birth were not consistently reported in the survey
and charges for newborns without complications are typically included in the
mother=s hospital bill. However, if
the newborn was discharged at a later date than the mother was discharged, then
the discharge was considered a separate stay for the newborn when constructing
the utilization and expenditure variables.
Some analysts may prefer to exclude zero night stays from inpatient analyses
and/or count these stays as ambulatory visits. Therefore, a separate use
variable is provided which contains a count of the number of inpatient events
where the reported dates of admission and discharge were the same (IPZERO97).
This variable can be subtracted from IPDIS97 to exclude Azero
night@ stays from inpatient
utilization estimates. In addition, separate expenditure variables are provided
for Azero night@
facility expenses (ZIFEXP97) and for separately billing doctor expenses
(ZIDEXP97). Analysts who choose to exclude zero-night stays from inpatient
expenditure analyses need to subtract the zero-night expenditure variable from
the corresponding expenditure variable for total inpatient stays (e.g.
IPFEXP97-ZIFEXP97 for facility expenses, IPDEXP97-ZIDEXP97 for separately
billing doctor expenses).
Dental Visits
The total number of dental visits variable (DVTOT97) includes those to any
person(s) for dental care including general dentists, dental hygienists, dental
technicians, dental surgeons, orthodontists, endodontists, and periodontists.
Additional variables are provided for the numbers of dental visits to general
dentists (DVGEN97) and to orthodontists (DVORTH97). For a small proportion of
sample persons, the sum of the general dentist and orthodontist visit variables
(DVGEN97+DVORTH97) is greater than the total number of dental visits (DVTOT97).
This result can only occur for persons who were reported to have seen both a
general dentist and orthodontist in the same visit(s). When this occurred,
expenditures for the visit were included as orthodontist expenses but not as
general dentist expenses. Expenditure variables for all three categories of
dental providers can be identified using the attached table in Appendix 3. Return To Table Of Contents
Home Health Care
In contrast to other types of medical events where data were collected on a
per visit basis, information on home health care utilization is collected in
MEPS on a per month basis. Variables are provided which indicate the total
number of days in 1997 where home health care was received from any type of paid
or unpaid caregiver (HHTOTD97), agencies, hospitals, or nursing homes (HHAGD97),
self-employed persons (HHINDD97), and unpaid informal caregivers not living with
the sample person (HHINFD97). The number of provider days represents the sum
across months of the number of days on which home health care was received, with
days summed across all providers seen. For example, if a person received care in
one month from one provider on 2 different days, then the number of provider
days would equal 2. The number of provider days would also equal 2 if a person
received care from 2 different providers on the same day. However, if a person
received care from 1 provider 2 times in the same day, then the provider days
would equal 1. These variables were assigned missing values if the number of
provider days could not be computed for any month in which the specific type of
home health care was received.
Separate expenditure variables are provided for agency-sponsored home health
care (includes care provided by home health agencies, hospitals, and nursing
homes) and care provided by self-employed persons. The attached table in
Appendix 3 identifies the home health care utilization and expenditure variables
contained in the file.
Vision Aids
Expenditure variables for the purchase of glasses and/or contact lenses are
identified in the attached table in Appendix 3. Due to the data collection
methodology, it was not possible to determine whether vision items that were
reported in round 3 had been purchased in 1997 or 1998. Therefore, expenses
reported in round 3 were only included if more than half of the person=s
reference period for the round was in 1997.
Other Medical Equipment and Services
This category includes expenditures for ambulance services, orthopedic items,
hearing devices, prostheses, bathroom aids, medical equipment, disposable
supplies, alterations/modifications, and other miscellaneous items or services
that were obtained, purchased or rented during the year. Respondents were only
asked once (in round 3) about their total annual expenditures and were not asked
about their frequency of use of these services. Expenditure variables
representing the combined expenses for these supplies and services are
identified in the Appendix 3 table. Return To Table Of Contents
Prescribed Medicines
There is one total utilization variable (RXTOT97) and 13 expenditure
variables included on the 1997 full-year file relating to prescribed medicines.
These 13 expenditure variables include an annual total expenditure variable
(RXEXP97) and 12 corresponding annual source of payment variables (RXSLF97,
RXMCR97, RXMCD97, RXPRV97, RXVA97, RXCHM97, RXOFD97, RXSTL97, RXWCP97, RXOSR97,
RXOPR97, and RXOPU97). Unlike the other event types, the prescribed medicine
events have some remaining inconsistencies in the data when comparing
information from the insurance section of the Household Component and source of
payment information from the Pharmacy Component (more specifically,
discrepancies between Medicare only household insurance responses and Medicaid
source of payment provided by pharmacy providers). These inconsistencies remain
unedited because there was strong evidence from the Pharmacy Component that
these were indeed Medicaid payments. All of these types of Household Component
events were either exact matches to events in the Pharmacy Component or refills
of exact matches, and in addition, all of these types of events were purchases
by persons with positive weights. The total utilization variable is a count of
all prescribed medications initially purchased or otherwise obtained during
1997, as well as any additional acquisitions of the medication. The total
expenditure variable sums all amounts paid out-of-pocket and by third party
payers for each prescription purchased in 1997. No variables reflecting charges
for prescription medicines are included because a large proportion of
respondents to the pharmacy component survey did not provide charge data (see
below).
Prescribed Medicines Data Collected
Data regarding prescription drugs were obtained through the household
questionnaire and a pharmacy component survey. During each round of the MEPS HC,
all respondents were asked to supply the name of any prescribed medication they
or their family members purchased or otherwise obtained during that round. For
each medication and in each round, the following information was collected:
whether any free samples of the medication were received; the name(s) of any
health problems the medication was prescribed for; the number of times the
prescription drug was obtained or purchased; the year, month, and day on which
the person first used the medication; and a list of the names, addresses, and
types of pharmacies that filled the household=s
prescriptions. Also, during the Household Component, respondents were asked if
they send in claim forms for their prescriptions (self-filers) or if their
pharmacy providers do this automatically for them at the point of purchase
(non-self-filers). For non-self-filers, charge and payment information was
collected in the pharmacy component survey. However, charge and payment
information was collected for self-filers in the household questionnaire,
because payments by private third party payers for self-filers’ purchases
would not be available from a pharmacy follow-back survey.
Pharmacy providers identified by the household were contacted by mail for the
pharmacy component survey if permission was obtained in writing from the person
with the prescription to release their pharmacy records. The signed permission
forms were provided to the various establishments prior to making any requests
for information. Each establishment was informed of all persons participating in
the survey that had prescriptions filled there in 1997 and a computerized
printout containing information about these prescriptions was sought. For each
medication listed, the following information was requested: date filled;
national drug code (NDC); medication name; strength of medicine (amount and
unit); quantity (package size and amount dispensed); total charge; and payments
by source.
When diabetic supplies, such as syringes and insulin, were reported in the
other medical supply section of the MEPS HC questionnaire as having been
obtained during the round, the interviewer was directed to collect information
on these items in the prescription drug section of MEPS. Data on expenses for
these items were collected in and imputed from the pharmacy component survey. Return To Table Of Contents
Prescribed Medicines Data Editing and Imputation
The general approach to preparing the household prescription data for this
file was to utilize the pharmacy component prescription data to assign
expenditure values to the household drug mentions. For self-filers, information
on payment sources was retained to the extent that these data were reported by
the household in the charge and payment section of the household questionnaire.
A matching program was adopted to link pharmacy survey drugs and the
corresponding drug information to household drug mentions. To improve the
quality of these matches, all drugs on the household and pharmacy files were
coded based on the medication names provided by the household and pharmacy, and
when available, the national drug code (NDC) provided in the pharmacy survey.
Considerable editing was done prior to the matching to correct data
inconsistencies in both data sets and fill in missing data and correct outliers
on the pharmacy file.
Drug price per unit outliers were analyzed on the pharmacy file by first
identifying the average wholesale unit price (AWUP) of the drug by linkage
through the NDC to a proprietary data base. In general, prescription drug unit
prices were deemed to be outliers by comparing unit prices reported in the
pharmacy data base to the AWUP and were edited, as necessary.
Round 3 household drug mentions in MEPS were not identified in the HC as 1997
or 1998 drug events for persons in households in which their Round 3 began in
1997 and ended in 1998. All exact matches to pharmacy survey drug events for
persons whose pharmacies participated were classified as 1997 drug purchases.
Any remaining Round 3 household drug mentions for persons with Round 3 spanning
both years were randomly allocated to 1997 or 1998 based on the proportion of
the household=s Round 3 period in each
year. Return To Table Of Contents
3.0 Survey Sample Information
3.1 Sample Design and Response Rates
The MEPS is designed to produce estimates at the national and
regional level over time for the civilian, noninstitutionalized population of
the United States and some subpopulations of interest. The health care
utilization data in this public use set pertain to calendar year 1997. The data
were collected in Rounds 1, 2, and 3 for MEPS Panel 2 and Rounds 3, 4, and 5 for
MEPS Panel 1. Note that Round 3 for a MEPS panel overlaps two calendar years.
The reference period for Round 3 of Panel 1 covers the end of 1997 and the
beginning of 1997 while the reference period for Round 3 of MEPS Panel 2 covers
the end of 1997 and the beginning of 1998. The only utilization data that appear
on the file are those associated with health care events occurring in calendar
year 1997.
The households in this 1997 MEPS database are related to
households participating in the National Health Interview Survey in 1995 and
1997. The households (occupied dwelling units) selected for MEPS Panel 1 were a
subsample of 1995 NHIS respondents while those in MEPS Panel 2 were a subsample
of 1997 NHIS respondents. A household may contain one or more family units, each
consisting of one or more individuals. Analysis can be undertaken using either
the individual or the family as the unit of analysis.
For MEPS Panel 2 several domains of interest were oversampled
to provide increased precision for analytic purposes. These domains included
households containing persons with one of the following characteristics based on
NHIS data: adults with functional impairments, children with limitations in
activity, individuals aged 18-64 with expected high medical expenditures,
individuals with family incomes expected to be below 200% of the poverty level
in 1997, and adults with other impairments. Because some households could be
associated with more than one domain, a hierarchical sample selection procedure
was employed. If a household could be associated with multiple domains, it was
assigned to the domain given the highest priority in the hierarchy.
For detailed information on the MEPS sample design for Panel
1, see Cohen, S. Sample Design of the 1996 Medical Expenditure Panel Survey
Household Component. Rockville (MD): Agency for Health Care Policy and Research;
1996. MEPS Methodology Report, No. 2. AHCPR Pub. No. 97-0027. For detailed
information on the MEPS sample design for Panel 2, see Appendix 2: Cohen, S.
Sample Design of the 1997 Medical Expenditure Panel Survey Household Component. Return To Table Of Contents
MEPS-Linked to the National Health Interview Survey
The sample of 10,639 households (occupied dwelling units) for
the MEPS Panel 1 consisted of a nationally representative subsample of the
households responding to the 1995 National Health Interview Survey (NHIS). A
subsample of 6,300 households was selected for MEPS Panel 2 from among
households responding to the 1996 NHIS.
The NHIS sample design has three stages of sample selection:
an area sample of PSUs; a sample of segments (single or groups of blocks or
block equivalents) within sampled PSUs; and a sample of housing units within
segments. Among initially sampled households, those containing Hispanics and
blacks were oversampled at rates of approximately 2 and 1.5 times the rate of
remaining households. These same rates of oversampling are reflected in the MEPS
sample of households. The only major difference in the definition of a household
between NHIS and MEPS is that college aged students living away from home during
the school year were interviewed at their place of residence for the NHIS but
were identified by and linked to their parents’ household for MEPS.
Sample Weights and Variance Estimation
In the database MEPS HC-020: 1997 Full Year Population
Characteristics weight variables are provided for estimation purposes.
Procedures and considerations associated with the construction and
interpretation of person and family level estimates using these and other
variables are discussed below.
Response Rates
In order to produce annual health care estimates for calendar
year 1997 based on the full MEPS sample, data will also need to be pooled across
the first two MEPS national samples. More specifically, full calendar year 1997
data collected in Rounds 3 through 5 for the MEPS Panel 1 sample are pooled with
data from the first three rounds of data collection for the MEPS Panel 2 sample
(illustrated below). Overall, the full 1997 MEPS household sample will consist
of approximately 13,000 reporting units which include 32,636 individuals that
completed the full series of MEPS interviews for their entire period of
eligibility, providing the necessary information to produce national use and
expenditure estimates for calendar year 1997.
301 Moved Permanently
301 Moved Permanently
Panel 1
Conditioned on response to Rounds 1-3 of the Panel 1 MEPS, of
21,696 key and inscope individuals eligible for data collection in 1997, 19,622
(90.44 percent) provided data for their entire period of eligibility.
Consequently, after factoring in the impact of survey attrition, the overall
Panel 1 MEPS person level response rate for deriving annual estimates was 63.5
percent (.702 x .9044). Of these full year respondents for calendar year 1997,
19,407 were in scope on December 31, 1997.
Panel 2
Conditioned on response to Round 1 of the Panel 2 MEPS, of
14, 644 key and inscope individuals eligible for data collection in 1997, 13,014
(88.87 percent) provided data for their entire period of eligibility.
Consequently, after factoring in the impact of survey attrition, the overall
Panel 2 MEPS person level response rate for deriving annual estimates was 69.2
percent (.779 x .8887). Of these full year respondents for calendar year 1997,
12,819 were in scope on December 31, 1997.
Combined MEPS Panels: Response Rate for Annual 1997 Estimates
For each independent MEPS sample, the estimation weights were
further adjusted for survey attrition over time. Each panel was then given equal
weight in the development of sampling weights to produce annual national
estimates. Therefore, a pooled response rate for the survey respondents in this
data set can be obtained by taking an average of the panel specific response
rates. This pooled response rate for the combined panels is 66.4 percent,
consisting of a total of 32,636 survey participants. The weighted MEPS
population estimate for the civilian non-institutionalized population as of
December 31, 1997 was 267,704,802, based on poststratification to population
estimates produced from the December 1997 Current Population Survey. Future
analyses will examine the impact of survey attrition on health care utilization
and expenditure estimates covering calendar year 1997. Return To Table Of Contents
3.2 Person Level Estimation using this MEPS PUF
Overview
There is a single person level weight variable called
WTDPER97. However, care should be taken in its application as it permits both
"point-in-time" and "range of time" estimates, depending on
the variables used to define the set of persons of interest for analysis. A
person level weight was assigned to each key, inscope person who responded to
MEPS for the full period of time that he or she was inscope during the MEPS
survey. For Panel 2 this requirement pertained only to 1997, but for Panel 1 it
pertained to both 1996 and 1997. (Recall that a person is inscope whenever he or
she is a member of the civilian, noninstitutionalized portion of the U.S.
population.)
Developing Person Level MEPS Estimates
The data in this file can be used to develop estimates on persons in the
civilian, noninstitutionalized population on December 31, 1997 and for the
slightly larger population of persons in the civilian, noninstitutionalized
population at any time during 1997. To obtain a cross-sectional (point-in-time)
estimate for all inscope persons living in the country on December 31, 1997,
include cases with both WTDPER97>0 (a positive person level weight) and
INSC1231=1 (the person is inscope on December 31, 1997). To obtain an estimate
for all persons who were inscope at some time in 1997, include all cases with
WTDPER97>0. After selecting the appropriate cases, apply the weight variable
WTDPER97 to the analytic variable(s) of interest to obtain national estimates.
The following table contains a summary of cases to include and sample sizes for
these two populations (for shorthand purposes the term "general" is
used to indicate the "civilian, noninstitutionalized" component of the
U.S.population).
|
Population of Interest |
Cases to Include |
Sample Size |
|
General Population on December 31, 1997 |
WTDPER97>0 and INSC1231=1 |
32,226 |
|
General Population over the course of 1997 |
WTDPER97>0 |
32,636 |
Return To Table Of Contents
Details on Person Weights Construction
Overview
The person level weight WTDPER97 was developed in three
stages. A person level weight for Panel 2 was created, including both an
adjustment for nonresponse over time and poststratification, controlling to
Current Population Survey (CPS) population estimates based on five different
variables. Poverty status was not included since income data for assigning
persons to a poverty status was yet to be established. Then a person level
weight for Panel 1 was created, again including an adjustment for nonresponse
over time and poststratification, controlling to CPS population estimates based
on the same five variables. In the meantime work proceeded on the MEPS income
data and the assignment of MEPS families to CPS-like family units, since the
assignment of poverty status is based on CPS family structures. When poverty
status information derived from income variables became available, a 1997
average annual weight was formed from the Panel 1 and Panel 2 weights by
multiplying the Panel weights by .5. Then a final poststratification was done on
this composite weight variable, including poverty status as well as the original
five poststratification variables in the establishment of the final 1997 person
level weight.
MEPS Panel 1
The person level weight for MEPS Panel 1 was developed using the 1996 full
year weight for an individual as a "base" weight for survey
participants present in 1996. For key, inscope respondents who joined an RU some
time in 1997 after being out-of-scope in 1996, the 1996 family weight associated
with the family the person joined served as a "base" weight. The
weighting process included an adjustment for nonresponse over Rounds 4 and 5 as
well as poststratification to population control totals from the CPS for
December, 1997. These control totals were derived by scaling back the population
totals obtained from the March 1998 CPS to reflect the December, 1997 CPS
estimated population distribution across age and sex categories as of December,
1997.
Variables used in the establishment of person level poststratification
control figures included: census region (Northeast, Midwest, South, West); MSA
status (MSA, non-MSA); race/ethnicity (Hispanic, black but non-Hispanic, and
other); sex, and age.
Overall, the weighted population estimate for the civilian,
noninstitutionalized population on December 31, 1997 is 267,704,802. Key,
responding persons not inscope on December 31, 1997 but inscope earlier in the
year retained, as their final Panel 1 weight, the weight after the nonresponse
adjustment.
MEPS Panel 2
The person level weight for MEPS Panel 2 was developed using
the MEPS Round 1 person-level weight as a "base" weight. For key,
inscope respondents who joined an RU after Round 1, the Round 1 family weight
served as a "base" weight. The weighting process included an
adjustment for nonresponse over Round 2 and the 1997 portion of Round 3 as well
as poststratification to the same population control figures for December 1997
used for the MEPS Panel 1 weights. The same five variables employed for Panel 1
poststratification (census region, MSA status, race/ethnicity, sex, and age)
were used for Panel 2 poststratification. As with Panel 1, Panel 2 key,
responding persons not inscope on December 31, 1997 but inscope earlier in the
year retained the weight after the nonresponse adjustment as their final Panel 2
weight.
Note that the MEPS round 1 weights (for both panels with one
exception as noted below) incorporated the following components: the original
household probability of selection for the NHIS; ratio-adjustment to NHIS-based
national population estimates at the household (occupied dwelling unit) level;
the probability of selection of dwelling units associated with the oversampling
of five population domains of analytic interest (for Panel 2 only); adjustment
for nonresponse at the dwelling unit level for Round 1; and poststratification
to figures at the family and person level obtained from the March 1997 CPS data
base. The five oversampled domains for Panel 2 were households with: persons
with functional impairments; children with limitations in activity; individuals
18-64 expected to incur high medical expenditures based on a statistical model;
persons with family incomes expected to be below 200 percent of poverty, based
on a statistical model; and adults with other impairments.
Return To Table Of Contents
The Final Weight for 1997
Variables used in the establishment of person level poststratification
control totals included: poverty status (below poverty, from 100 to 125 percent
of poverty, from 125 to 200 percent of poverty, from 200 to 400 percent of
poverty, at least 400 percent of poverty); census region (Northeast, Midwest,
South, West); MSA status (MSA, non-MSA); race/ethnicity (Hispanic, black but
non-Hispanic, and other); sex, and age. Overall, the weighted population
estimate for the civilian, noninstitutionalized population for December 31, 1997
is 267,704,802 (WTDPER97>0 and INSC1231=1). The inclusion of key, inscope
persons who were not inscope on December 31, 1997 brings the estimated total
number of persons represented by the MEPS respondents over the course of the
year, to 270,965,010 (WTDPER97>0).
The weights for persons who died while members of the civilian,
noninstitutionalized population in 1997 were adjusted separately for persons
under age 65 and those age 65 and older. Control figures were derived from Vital
Statistics death registries, the Nursing Home Component of the 1996 MEPS, and
the annual Medicare Beneficiary Survey (MCBS).
The weights for persons ascertained to be living in nursing homes for at
least one day in 1997 and who were not inscope on December 31, 1997 were
adjusted to a control figure derived from the Nursing Home Component of the 1996
MEPS.
Coverage
The target population for MEPS is the 1997 U.S. civilian,
noninstitutionalized population. However, the MEPS sampled households are a
subsample of the NHIS households interviewed in 1995 (Panel 1) and 1996 (Panel
2). New households created after the NHIS interviews for the respective Panels
and consisting exclusively of persons who entered the target population after
1995 (Panel 1) or after 1996 (Panel 2) are not covered by MEPS. These would
include families consisting solely of: immigrants; persons leaving the military;
U.S. citizens returning from residence in another country; and persons leaving
institutions. It should be noted that this set of uncovered persons constitutes
only a tiny proportion of the MEPS target population.
Return To Table Of Contents
3.3 Family Level Estimation Using this MEPS PUF
There are two family weight variables called WTFAMF97 and
WTCFAM97 that are provided in this release. In general, WTFAMF97 can be used to
make estimates for the cross-section of families in the U.S. civilian,
noninstitutionalized population on December 31, 1997 where families are
identified based on the MEPS definition of a family unit. WTCFAM97 is provided
to permit the capability of producing estimates for families defined according
to the guidelines used by the Current Population Survey (CPS). Such family units
are characterized here as "CPS-like". In addition, estimates can be
constructed using WTFAMF97. These estimates permit the inclusion of: 1) MEPS
families that existed at some time during 1997 but whose members became
out-of-scope prior to the end of the year (e.g., all family members moved out of
the country, died, etc.) and 2) MEPS families in existence on December 31, 1997. Return To Table Of Contents
Definition of Family Estimates
A family is defined in MEPS as two or more persons living
together in the same household who are related by blood, marriage, or adoption,
as well as foster children. Other MEPS families include unmarried persons living
together who consider themselves a family unit. Single persons living with
neither a relative nor a person identified as a "significant other"
have also been assigned a family ID value as and a family level weight, and thus
can be included or excluded from estimates, as desired. Relatives identified as
usual residents of the household who were not there at the time of the
interview, such as college students living away from their parents’ home
during the school year, were considered as members of the family that identified
them.
To make estimates at the family level, it is necessary to
prepare a family level file containing one record per family (see instructions
below), family level summary characteristics, and the family-level weight
variable (WTFAMF97). Each MEPS family unit is uniquely identified by the
combination of the variables DUID and FAMIDYR. The number of persons in a MEPS
sample family ranges from 1 to 14 (the positive values for FAMSZEYR). Only
persons with positive nonzero family weight values (WTFAMF97>0) are
candidates for inclusion in family estimates.
Three sets of families for whom estimates can be obtained are
defined in the table below (along with respective sample sizes). Persons with
FMRS1231=1 were inscope for the survey on 12/31/97 and therefore part of a MEPS
family on 12/31/97. The more expansive definition of families (second row in
table) includes families and members of families who were not inscope at the end
of the year. The third row is for CPS-like families, and thus excludes foster
children. While MEPS includes individual persons as family units (about
one-third of all units) to cover the entire civilian, noninstitutionalized
population, analysts may restrict their analyses to families with 2 or more
members using the family size variables shown in the table. Return To Table Of Contents
|
Population of Interest |
Cases to Include |
Sample Size |
Family Size Variable |
|
Cross-section of Families in the Civilian Noninstitutionalized
Population on 12/31/97 |
WTFAMF97>0 & FMRS1231=1 |
12,970 |
FAMS1231 |
|
Families in the Civilian Noninstitutionalized Population on 12/31/97 plus
families and members of families in existence earlier in 1997 who were not
part of the civilian noninstitutionalized population on 12/31/97 |
WTFAMF97>0 |
13,087 |
FAMSZEYR |
|
CPS-like families excluding foster children |
WTCFAM97>0 |
13,246 |
FCSZ1231 |
Instructions to Create Family Estimates
The following is a summary of the steps and the variables to be used for
family level estimation based on the MEPS type definition of families.
- Concatenate the variables DUID and FAMIDYR into a new variable (e.g.
DUIDFAMY).
- To create a family level file, sort by DUIDFAMY and then subset to one
record per DUIDFAMY value by retaining only the reference person record
(FAMRFPYR=1) for each value of DUIDFAMY. If aggregate measures for families
are needed for analytic purposes (e.g. means or totals), then those measures
need to be computed using person-level information within families and
attached to the family record. For other types of variables, analysts
frequently use the characteristics of the reference person to represent
family characteristics.
- Apply the weight WTFAMF97 to the analytic variable(s) of interest to obtain
national family estimates.
- Use CPSFAMID, FCRP1231, and WTCFAM97 in place of FAMIDYR, FAMRFPYR, and
WTFAMF97, respectively, to make estimates as of 12/31/97 for CPS-like families
(thus excluding foster children).
Return To Table Of Contents
Details on Family Weight Construction and Estimated Number of
Families
To develop the family level weight (WTFAMF97), the person
level weight (WTDPER97) of the family reference person (FAMRFPYR=1) was used as
the "base" weight for all responding full year families. Then, for
responding families eligible for weighting and in existence at the end of 1997,
these "base" weights were poststratified to population control figures
from the Current Population Survey (CPS) for December 1997 (these figures were
derived by scaling the population totals obtained from the March 1997 CPS to
reflect family estimates as of December, 1997). The family level
poststratification incorporated the following variables: poverty status (below
poverty, from 100 to 125 percent of poverty, from 125 to 200 percent of poverty,
from 200 to 400 percent of poverty, at least 400 percent of poverty); census
region; MSA status; race/ethnicity of reference person (Hispanic, black but non
Hispanic, and other); family type (reference person married, living with spouse;
male reference person, unmarried or spouse not present; female reference person,
unmarried or spouse not present); age of reference person; and family size as of
December 31, 1997.
Overall, the weighted population estimate for the number of
MEPS family units containing at least one member of the U.S. civilian,
noninstitutionalized population on December 31, 1997 is 111,014,574 (those
families whose members have WTFAMF97>0 and FMRS1231=1). The inclusion of
families whose members left the inscope population prior to December 31, 1997
brought the estimated total number of families represented by the MEPS
responding families to 112,165,786 (those families whose members have
WTFAMF97>0). The estimated total number of CPS-like families is 113,295,487
(those families whose members have WTCFAM97>0). Return To Table Of Contents
Variance Estimation
To obtain estimates of variability (such as the standard
error of sample estimates or corresponding confidence intervals) for estimates
based on MEPS survey data, the complex sample design of MEPS for both person and
family level analyses must be taken into account. Various approaches can be used
to develop such estimates of variance including use of the Taylor series or
replication methodologies. Replicate weights have not been developed for the
MEPS 1997 data.
Using a Taylor Series approach, variance estimation strata
and the variance estimation PSUs within these strata must be specified. The
corresponding variables on the 1997 MEPS full year utilization database are
VARSTR97 and VARPSU97, respectively. Specifying a "with replacement"
design in a computer software package, such as SUDAAN, should provide standard
errors appropriate for assessing the variability of MEPS survey estimates. It
should be noted that the number of degrees of freedom associated with estimates
of variability indicated by such a package may not appropriately reflect the
actual number available. For MEPS sample estimates for characteristics generally
distributed throughout the country (and thus the sample PSUs), there are over
100 degrees of freedom for the 1997 full year data associated with the
corresponding estimates of variance. Return To Table Of Contents
D. Variable-Source Crosswalk
SURVEY ADMINISTRATION VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
DUID |
DU ID |
Assigned in Sampling |
|
PID |
Person Number (PN) |
Assigned in Sampling or by CAPI |
|
DUPERSID |
Sample Person ID (DU+PN) |
Assigned in Sampling |
|
PANEL97 |
Panel Number |
Constructed |
|
FAMID31 |
Family Identifier (Student Merged In) – R31 |
CAPI Derived |
|
FAMID42 |
Family Identifier (Student Merged In) – R42 |
CAPI Derived |
|
FAMID53 |
Family Identifier (Student Merged In) – R53 |
CAPI Derived |
|
FAMID97 |
Fam Identifier (Stud Merged In) - 12/31/97 |
CAPI Derived |
|
FAMIDYR |
Annual Family Identifier |
Constructed |
|
CPSFAMID |
CPS-Like Family Identifier |
Constructed |
|
FCSZ1231 |
Family Size Responding 12/31 CPS Family |
Constructed |
|
FCRP1231 |
Ref Person of 12/31 CPS Family |
Constructed |
|
RULETR31 |
RU Letter – R31 |
CAPI Derived |
|
RULETR42 |
RU Letter – R42 |
CAPI Derived |
|
RULETR53 |
RU Letter – R53 |
CAPI Derived |
|
RULETR97 |
RU Letter As of Dec 31 |
CAPI Derived |
|
RUSIZE31 |
RU Size – R31 |
CAPI Derived |
|
RUSIZE42 |
RU Size – R42 |
CAPI Derived |
|
RUSIZE53 |
RU Size – R53 |
CAPI Derived |
|
RUSIZE97 |
RU Size As of Dec 31 |
CAPI Derived |
|
RUCLAS31 |
RU: Standard/New/Student – R31 |
CAPI Derived |
|
RUCLAS42 |
RU: Standard/New/Student – R42 |
CAPI Derived |
|
RUCLAS53 |
RU: Standard/New/Student – R53 |
CAPI Derived |
|
RUCLAS97 |
RU: Standard/New/Student - 12/31/97 |
CAPI Derived |
|
FAMSZE31 |
RU Size Including Students – R31 |
CAPI Derived |
|
FAMSZE42 |
RU Size Including Students – R42 |
CAPI Derived |
|
FAMSZE53 |
RU Size Including Students – R53 |
CAPI Derived |
|
FAMSZE97 |
RU Size Including Students As of Dec 31 |
CAPI Derived |
|
FMRS1231 |
Member of Responding 12/31 Family |
Constructed |
|
FAMS1231 |
Family Size of Responding 12/31 Family |
Constructed |
|
FAMSZEYR |
Size of Responding Annualized Family |
Constructed |
|
FAMRFPYR |
Reference Person of Annualized Family |
Constructed |
|
FYFAMTYP |
CPS –Full Year Family Type |
Constructed |
|
INRU1231 |
Person Was In RU On 12/31/97 |
Constructed |
|
REGION31 |
Census Region – R31 |
Assigned in Sampling |
|
REGION42 |
Census Region – R42 |
Assigned in Sampling |
|
REGION53 |
Census Region – R53 |
Assigned in Sampling |
|
REGION97 |
Census Region As Of Dec 31 |
Assigned in Sampling |
|
MSA53 |
MSA – R53 |
Assigned in Sampling |
|
MSA97 |
MSA As Of Dec 31 |
Assigned in Sampling |
|
REFPRS31 |
Reference Person At Round 31 |
RE 42-45 |
|
REFPRS42 |
Reference Person At Round 42 |
RE 42-45 |
|
REFPRS53 |
Reference Person At Round 53 |
RE 42-45 |
|
REFPRS97 |
Reference Person As Of Dec 31 |
RE 42-45 |
|
RESP31 |
1st Respondent Indicator For Rnd 31 |
RE 6, 8 |
|
RESP42 |
1st Respondent Indicator For Rnd 42 |
RE 6, 8 |
|
RESP53 |
1st Respondent Indicator For Rnd 42 |
RE 6, 8 |
|
RESP97 |
1st Respondent Indicator As Of 12/31/97 |
RE 6, 8 |
|
PROXY31 |
Was Respondent A Proxy In R31 |
RE 2 |
|
PROXY42 |
Was Respondent A Proxy In R42 |
RE 2 |
|
PROXY53 |
Was Respondent A Proxy In R53 |
RE 2 |
|
PROXY97 |
Was Respondent A Proxy As Of 12/31/97 |
RE 2 |
|
BEGRFD31 |
R31 Reference Period Begin Date: Day |
CAPI Derived |
|
BEGRFM31 |
R31 Reference Period Begin Date: Month |
CAPI Derived |
|
BEGRFY31 |
R31 Reference Period Begin Date: Year |
CAPI Derived |
|
ENDRFD31 |
Reference Period End Date: Day – R31 |
CAPI Derived |
|
ENDRFM31 |
Reference Period End Date: Month – R31 |
CAPI Derived |
|
ENDRFY31 |
Reference Period End Date: Year – R31 |
CAPI Derived |
|
BEGRFD42 |
R42 Reference Period Begin Date: Day |
CAPI Derived |
|
BEGRFM42 |
R42 Reference Period Begin Date: Month |
CAPI Derived |
|
BEGRFY42 |
R42 Reference Period Begin Date: Year |
CAPI Derived |
|
ENDRFD42 |
Reference Period End Date: Day – R42 |
CAPI Derived |
|
ENDRFM42 |
Reference Period End Date: Month – R42 |
CAPI Derived |
|
ENDRFY42 |
Reference Period End Date: Year – R42 |
CAPI Derived |
|
BEGRFD53 |
R53 Reference Period Begin Date: Day |
CAPI Derived |
|
BEGRFM53 |
R53 Reference Period Begin Date: Month |
CAPI Derived |
|
BEGRFY53 |
R53 Reference Period Begin Date: Year |
CAPI Derived |
|
ENDRFD53 |
Reference Period End Date: Day – R53 |
CAPI Derived |
|
ENDRFM53 |
Reference Period End Date: Month – R53 |
CAPI Derived |
|
ENDRFY53 |
Reference Period End Date: Year – R53 |
CAPI Derived |
|
ENDRFD97 |
1997 Reference Period End Date: Day |
RE Section |
|
ENDRFM97 |
1997 Reference Period End Date: Month |
RE Section |
|
ENDRFY97 |
1997 Reference Period End Date: Year |
RE Section |
|
KEYNESS |
Person Key Status |
RE Section |
|
INSCOP31 |
Inscope – R31 |
RE Section |
|
INSCOP42 |
Inscope – R42 |
RE Section |
|
INSCOP53 |
Inscope – R53 |
RE Section |
|
INSCOP97 |
Inscope – R53 Start Through 12/31/97 |
RE Section |
|
INSC1231 |
Inscope Status on 12/31/97 |
Constructed |
|
INSCOPE |
Was Person Ever Inscope In 1997 |
RE Section |
|
ELGRND31 |
Eligibility – R31 |
RE Section |
|
ELGRND42 |
Eligibility – R42 |
RE Section |
|
ELGRND53 |
Eligibility – R53 |
RE Section |
|
ELGRND97 |
Eligibility – R53 Start Through 12/31/97 |
RE Section |
|
ELIGIBLE |
Was Person Ever Eligible In 1997 |
RE Section |
|
PSTATS31 |
Person Disposition Status – R31 |
RE Section |
|
PSTATS42 |
Person Disposition Status – R42 |
RE Section |
|
PSTATS53 |
Person Disposition Status – R53 |
RE Section |
|
RURSLT31 |
RU Result – R31 |
Assigned by CAPI |
|
RURSLT42 |
RU Result – R42 |
Assigned by CAPI |
|
RURSLT53 |
RU Result – R53 |
Assigned by CAPI |
Return To Table Of Contents
DEMOGRAPHIC VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
AGE31X |
Age – R31 (Edited/Imputed) |
RE 12, 57-66 |
|
AGE42X |
Age – R42 (Edited/Imputed) |
RE 12, 57-66 |
|
AGE53X |
Age – R53 (Edited/Imputed) |
RE 12, 57-66 |
|
AGE97X |
Age - 12/31/97 (Edited/Imputed) |
RE 12, 57-66 |
|
DOBMM |
Date of Birth: Month |
RE 12, 57-66 |
|
DOBYY |
Date of Birth: Year |
RE 12, 57-66 |
|
SEX |
Sex |
RE 12, 57, 61 |
|
RACEX |
Race (Edited/Imputed) |
RE 101, 102 |
|
RACETHNX |
Race/Ethnicity (Edited/Imputed) |
RE 98-102 |
|
HISPANX |
Hispanic Ethnicity (Edited/Imputed) |
RE 98-100 |
|
HISPCAT |
Specific Hispanic Ethnicity Group |
RE 98-100 |
|
MARRY31X |
Marital Status – R31 (Edited/Imputed) |
RE 13, 97 |
|
MARRY42X |
Marital Status – R42 (Edited/Imputed) |
RE 13, 97 |
|
MARRY53X |
Marital Status – R53 (Edited/Imputed) |
RE 13, 97 |
|
MARRY97X |
Marital Status - 12/31/97 (Edited/Imputed) |
RE 13, 97 |
|
SPOUID31 |
Spouse ID – R31 |
RE 13, 76, 77, 97 |
|
SPOUID42 |
Spouse ID – R42 |
RE 13, 76, 77, 97 |
|
SPOUID53 |
Spouse ID – R53 |
RE 13, 76, 77, 97 |
|
SPOUID97 |
Spouse ID - 12/31/97 |
RE 13, 76, 77, 97 |
|
SPOUIN31 |
Marital Status W/ Spouse Present – R31 |
RE 13, 76, 77, 97 |
|
SPOUIN42 |
Marital Status W/ Spouse Present – R42 |
RE 13, 76, 77, 97 |
|
SPOUIN53 |
Marital Status W/ Spouse Present – R53 |
RE 13, 76, 77, 97 |
|
SPOUIN97 |
Marital Status W/Spouse Present - 12/31/97 |
RE 13, 76, 77, 97 |
|
EDUCYR31 |
Completed Years of Education – R31 |
RE 103-105 |
|
EDUCYR42 |
Completed Years of Education – R42 |
RE 103-105 |
|
EDUCYR53 |
Completed Years of Education – R53 |
RE 103-105 |
|
EDUCYR97 |
Completed Years of Education - 12/31/97 |
RE 103-105 |
|
HIDEG31 |
Highest Degree – R31 |
RE 103-105 |
|
HIDEG42 |
Highest Degree – R42 |
RE 103-105 |
|
HIDEG53 |
Highest Degree – R53 |
RE 103-105 |
|
HIDEG97 |
Highest Degree - 12/31/97 |
RE 103-105 |
|
FTSTU31X |
Student Status If Ages 17-23 - Round 31 |
RE 11A, 106-108 |
|
FTSTU42X |
Student Status If Ages 17-23 - Round 42 |
RE 11A, 106-108 |
|
FTSTU53X |
Student Status If Ages 17-23 - Round 53 |
RE 11A, 106-108 |
|
FTSTU97X |
Student Status If Ages 17-23 - 12/31/97 |
RE 11A, 106-108 |
|
ACTDTY31 |
Military Full-Time Active Duty – R31 |
RE14, 96A |
|
ACTDTY42 |
Military Full-Time Active Duty – R42 |
RE 14, 96B1 |
|
ACTDTY53 |
Military Full-Time Active Duty – R53 |
RE 14, 96B1 |
|
DIDSERVE |
Ever Served In Armed Forces |
RE 18, 95 |
|
VETPVIET |
Served In Post-Vietnam Era |
RE 35, 94, 94A, 95, 96 |
|
VETVIET |
Served In Vietnam War Era |
RE 35, 94, 94A, 95, 96 |
|
VETKOR |
Served In Korean War Era |
RE 35, 94, 94A, 95, 96 |
|
VETWW |
Served In WWI Or WW2 Era |
RE 35, 94, 94A, 95, 96 |
|
VETOTH |
Served In Other Period |
RE 35, 94, 94A, 95, 96 |
|
RFREL31X |
Relation To Ref Pers - R31 (Edited/Imputed) |
RE 76-77 |
|
RFREL42X |
Relation To Ref Pers - R42 (Edited/Imputed) |
RE 76-77 |
|
RFREL53X |
Relation To Ref Pers - R53 (Edited/Imputed) |
RE 76-77 |
|
RFREL97X |
Relation To Ref Pers 12/31/97 (Edit/Imp) |
RE 76-77 |
|
MOPID31X |
PID Of Person's Mom (Edited/Imputed) |
RE 76-77 |
|
MOPID42X |
PID Of Person's Mom (Edited/Imputed) |
RE 76-77 |
|
MOPID53X |
PID Of Person's Mom (Edited/Imputed) |
RE 76-77 |
|
DAPID31X |
PID Of Person's Dad (Edited/Imputed) |
RE 76-77 |
|
DAPID42X |
PID Of Person's Dad (Edited/Imputed) |
RE 76-77 |
|
DAPID53X |
PID Of Person's Dad (Edited/Imputed) |
RE 76-77 |
Return To Table Of Contents
INCOME VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
SSIDIS97 |
SSI RECEIPT DUE TO DISABILITY |
IN 39 |
|
AFDC97 |
DID PERSON’S CHECK INCLUDE AFDC OR ADC |
IN 44 |
|
FILEDR97 |
HAS PERSON FILED A FED INCOME TAX RETURN |
IN 2 |
|
WILFIL97 |
WILL PERSON FILE FED INCOME TAX RETURN |
IN 3 |
|
FLSTAT97 |
PERSON’S FILING STATUS |
IN 4 |
|
FILER97 |
PRIMARY OR SECONDARY FILER |
IN 4 |
|
JTINRU97 |
JOINT FILER’S MEMBERSHIP IN RU |
IN 5 |
|
JNTPID97 |
PID OF SECONDARY FILER |
IN 5 |
|
CLMDEP97 |
DID/WILL PERS CLAIM DEPENDENTS ON RETURN |
IN 6 |
|
DEPDNT97 |
PERSON IS FLAGGED A DEPENDENT |
IN 7 |
|
DPINRU97 |
DEPENDENTS IN/OUT OF RU |
IN 7 |
|
DPOTSD97 |
HOW MANY DEPENDENTS LIVE OUTSIDE RU |
IN 8 |
|
TAXFRM97 |
TAX FORM PERSON WILL FILE |
IN 9 |
|
DEDUCT97 |
ITEMIZE OR STANDARD DEDUCTION |
IN 10 |
|
ITMEXP97 |
WILL PERSON ITEMIZE MEDICAL EXPENSE |
IN 11 |
|
MEXAMT97 |
TOTAL AMOUNT FOR MEDICAL EXPENSES |
IN 12 |
|
NTMDED97 |
PERSON’S NET MEDICAL EXPENSE DEDUCTION |
IN 13 |
|
TOTDED97 |
TOTAL OF ALL ITEMIZED DEDUCTIONS |
IN 14 |
|
CLMHIP97 |
DID/WILL PERS DEDUCT HEALTH INSUR PREM |
IN 15 |
|
ELDISC97 |
DID/WILL PERS RECEIVE ELDERLY/DISAB CRED |
IN 16 |
|
EICRDT97 |
DID/WILL PERS RECEIVE EARNED INC CREDIT |
IN 17 |
|
UNEMTX97 |
TAXABLE PERCENTAGE OF UNEMPLOYMENT |
IN 30 |
|
INTRTX97 |
TAXABLE PERCENTAGE OF INTEREST |
IN 19 |
|
SSECTX97 |
TAXABLE PERCENTAGE OF SOCIAL SECURITY |
IN 31 |
|
IRATAX97 |
TAXABLE PERCENTAGE OF IRA INCOME |
IN 25 |
|
FOODST97 |
DID ANYONE PURCHASE FOOD STAMPS |
IN 55 |
|
FOODMN97 |
NUMBER OF FOOD STAMPS PURCHASED |
IN 56 |
|
FOODCT97 |
AMOUNT FAMILY PAID FOR FOOD STAMPS |
IN 57 |
|
FOODVL97 |
MONTHLY VALUE OF FOOD STAMPS |
IN 58 |
|
TTLP97X |
PERSON’S TOTAL INCOME |
Constructed |
|
POVCAT97 |
FAMILY INCOME AS PERCENT OF POVERTY LINE |
Constructed |
|
WAGEP97X |
PERSON’S WAGE INCOME |
Constructed |
|
WAGIMP97 |
WAGEPN IMPUTATION FLAG |
Constructed |
|
BUSNP97X |
PERSON’S BUSINESS INCOME |
Constructed |
|
BUSIMP97 |
BUSNPN IMPUTATION FLAG |
Constructed |
|
FARMP97X |
PERSON’S FARM INCOME |
Constructed |
|
FARIMP97 |
FARMPN IMPUTATION FLAG |
Constructed |
|
UNEMP97X |
PERSON’S UNEMPLOYMENT COMP INCOME |
Constructed |
|
UNEIMP97 |
UNEMPN IMPUTATION FLAG |
Constructed |
|
WCMPP97X |
PERSON’S WORKMAN’S COMPENSATION |
Constructed |
|
WCPIMP97 |
WCMPPN IMPUTATION FLAG |
Constructed |
|
INTRP97X |
PERSON’S INTEREST INCOME |
Constructed |
|
INTIMP97 |
INTRPN IMPUTATION FLAG |
Constructed |
|
DIVDP97X |
PERSON’S DIVIDEND INCOME |
Constructed |
|
DIVIMP97 |
DIVDPN IMPUTATION FLAG |
Constructed |
|
SALEP97X |
PERSON’S SALES INCOME |
Constructed |
|
SALIMP97 |
SALEPN IMPUTATION FLAG |
Constructed |
|
PENSP97X |
PERSON’S PENSION INCOME |
Constructed |
|
PENIMP97 |
PENSPN IMPUTATION FLAG |
Constructed |
|
SSECP97X |
PERSON’S SOCIAL SECURITY INCOME |
Constructed |
|
SSCIMP97 |
SSECPN IMPUTATION FLAG |
Constructed |
|
TRSTP97X |
PERSON’S TRUST/RENT INCOME |
Constructed |
|
TRTIMP97 |
TRSTPN IMPUTATION FLAG |
Constructed |
|
VETSP97X |
PERSON’S VETERAN’S INCOME |
Constructed |
|
VETIMP97 |
VETSPN IMPUTATION FLAG |
Constructed |
|
IRASP97X |
PERSON’S IRA INCOME |
Constructed |
|
IRAIMP97 |
IRASPN IMPUTATION FLAG |
Constructed |
|
REFDP97X |
PERSON’S REFUND INCOME |
Constructed |
|
REFIMP97 |
REFDPN IMPUTATION FLAG |
Constructed |
|
ALIMP97X |
PERSON’S ALIMONY INCOME |
Constructed |
|
ALIIMP97 |
ALIMPN IMPUTATION FLAG |
Constructed |
|
CHLDP97X |
PERSON’S CHILD SUPPORT |
Constructed |
|
CHLIMP97 |
CHLDPN IMPUTATION FLAG |
Constructed |
|
CASHP97X |
PERSON’S OTHER REGULAR CASH CONTRIB |
Constructed |
|
CSHIMP97 |
CASHPN IMPUTATION FLAG |
Constructed |
|
SSIP97X |
PERSON’S SSI |
Constructed |
|
SSIIMP97 |
SSIPN IMPUTATION FLAG |
Constructed |
|
PUBP97X |
PERSON’S PUBLIC ASSISTANCE |
Constructed |
|
PUBIMP97 |
PUBPN IMPUTATION FLAG |
Constructed |
|
OTHRP97X |
PERSON’S OTHER INCOME |
Constructed |
|
OTHIMP97 |
OTHRPN IMPUTATION FLAG |
Constructed |
Return To Table Of Contents
EMPLOYMENT VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
EMPST31 |
Employment Status Rd 3/1 |
EM 1-3; RJ 1, 6 |
|
EMPST42 |
Employment Status Rd 4/2 |
EM 1-3; RJ 1, 6 |
|
EMPST53 |
Employment Status Rd 5/3 |
EM 1-3; RJ 1, 6 |
|
RNDFLG31 |
Data Collection Round for Rd 3/1 CMJ |
Constructed |
|
MORJOB31 |
Has More Than One Job Rd 3/1 Int Date |
EM 1-4, 51; RJ 1, 6; Constructed |
|
MORJOB42 |
Has More Than One Job Rd 4/2 Int Date |
EM 1-4, 51; RJ 1, 6; Constructed |
|
MORJOB53 |
Has More Than One Job Rd 5/3 Int Date |
EM 1-4, 51; RJ 1, 6; Constructed |
|
EVRWRK |
Ever Worked For Pay in Life as of 12/31/97 |
EM 1-4, 51; RJ 1, 6; Constructed |
|
HRWG31X |
Hourly Wage Rd 3/1 CMJ |
EW 5, 7, 11-13, 17-18, 24; EM 104, 111 |
|
HRWG42X |
Hourly Wage Rd 4/2 CMJ |
EW 5, 7, 11-13, 17-18, 24; EM 104, 111 |
|
HRWG53X |
Hourly Wage Rd 5/3 CMJ |
EW 5, 7, 11-13, 17-18, 24; EM 104, 111 |
|
HRWGIM31 |
HRWG31X Imputation Flag |
Constructed |
|
HRWGIM42 |
HRWG42X Imputation Flag |
Constructed |
|
HRWGIM53 |
HRWG53X Imputation Flag |
Constructed |
|
HRHOW31 |
How Hourly Wage Was Calculated R3/1 |
EM 2-3, 51, 104, 111; EW 2-24 |
|
HRHOW42 |
How Hourly Wage Was Calculated R4/2 |
EM 2-3, 51, 104, 111; EW 2-24 |
|
HRHOW53 |
How Hourly Wage Was Calculated R5/3 |
EM 2-3, 51, 104, 111; EW 2-24 |
|
HOUR31 |
Hours Per Week at RD 3/1 CMJ |
EM 1-3, 51, 104-105, 111; EW 17 |
|
HOUR42 |
Hours Per Week at RD 4/2 CMJ |
EM 1-3, 51, 104-105, 111; EW 17 |
|
HOUR53 |
Hours Per Week at RD 5/3 CMJ |
EM 1-3, 51, 104-105, 111; EW 17 |
|
SELFCM31 |
Self-Employed at RD 3/1 CMJ |
EM 1-3, 51; RJ 01 |
|
SELFCM42 |
Self-Employed at RD 4/2 CMJ |
EM 1-3, 51; RJ 01 |
|
SELFCM53 |
Self-Employed at RD 5/3 CMJ |
EM 1-3, 51; RJ 01 |
|
DISVW31X |
Disavowed Health Insurance at R3/1 CMJ |
EM113, 117; RJ07, 08, 08A; HX and OE Sections |
|
DISVW42X |
Disavowed Health Insurance at R4/2 CMJ |
EM113, 117; RJ07, 08, 08A, HX and OE Sections |
|
DISVW53X |
Disavowed Health Insurance at R5/3 CMJ |
EM113, 117; RJ07, 08, 08A; HX and OE Sections |
|
CHOIC31 |
Choice of Health Plans at Rd 3/1 CMJ |
EM 1-3, 51, 96, 113-115, 124; RJ08 |
|
CHOIC42 |
Choice of Health Plans at Rd 4/2 CMJ |
EM 1-3, 51, 96, 113-115, 124; RJ08 |
|
CHOIC53 |
Choice of Health Plans at Rd 5/3 CMJ |
EM 1-3, 51, 96, 113-115, 124; RJ08 |
|
CIND31 |
Condensed Industry Code Rd 3/1 CMJ |
EM 97-100; RJ01; Constructed |
|
CIND42 |
Condensed Industry Code Rd 4/2 CMJ |
EM 97-100; RJ01; Constructed |
|
CIND53 |
Condensed Industry Code Rd 5/3 CMJ |
EM 97-100; RJ01; Constructed |
|
NUMEMP31 |
Number of Employees at Rd 3/1 CMJ |
EM 91-92, 124; RJ01 |
|
NUMEMP42 |
Number of Employees at Rd 4/2 CMJ |
EM 91-92, 124; RJ01 |
|
NUMEMP53 |
Number of Employees at Rd 5/3 CMJ |
EM 91-92, 124; RJ01 |
|
MORE31 |
Rd 3/1 CMJ Firm Has More Than One Location |
EM 1-3, 51, 94; RJ01 |
|
MORE42 |
Rd 4/2 CMJ Firm Has More Than One Location |
EM 1-3, 51, 94; RJ01 |
|
MORE53 |
Rd 5/3 CMJ Firm Has More Than One Location |
EM 1-3, 51, 94; RJ01 |
|
UNION31 |
Union Status at Rd 3/1 CMJ |
EM 1-3, 51, 96, 116; RJ01 |
|
UNION42 |
Union Status at Rd 4/2 CMJ |
EM 1-3, 51, 96, 116; RJ01 |
|
UNION53 |
Union Status at Rd 5/3 CMJ |
EM 1-3, 51, 96, 116; RJ01 |
|
NWK31 |
Reason Not Working During Rd 3/1 |
EM 1-3, 101-102, 126-127, 132-133, 138-139, 141, 141.OV; RJ10 |
|
NWK42 |
Reason Not Working During Rd 4/2 |
EM 1-3, 101-102, 126-127, 132-133, 138-139, 141, 141.OV; RJ10 |
|
NWK53 |
Reason Not Working During Rd 5/3 |
EM 1-3, 101-102, 126-127, 132-133, 138-139, 141, 141.OV; RJ10 |
|
CHGJ3142 |
Changed Job Between Rd 3/1 and Rd 4/2 |
RJ01, 01A |
|
CHGJ4253 |
Changed Job Between Rd 4/2 and Rd 5/3 |
RJ01, 01A |
|
YCHJ3142 |
Why Chngd Job Between Rd 3/1 and Rd 4/2 |
RJ10, 10.OV |
|
YCHJ4253 |
Why Chngd Job Between Rd 4/2 and Rd 5/3 |
RJ10, 10.OV |
|
STJBMM31 |
Month Started Rd 3/1 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBDD31 |
Day Started Rd 3/1 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBYY31 |
Year Started Rd 3/1 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBMM42 |
Month Started Rd 4/2 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBDD42 |
Day Started Rd 4/2 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBYY42 |
Year Started Rd 4/2 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBMM53 |
Month Started Rd 5/3 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBDD53 |
Day Started Rd 5/3 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
STJBYY53 |
Year Started Rd 5/3 CMJ |
EM10, 10.OV, 10.OV2; RJ01, 01A |
|
EVRETIRE |
Person Has Ever Retired |
EM 1-3, 101-102, 126-127, 132-133, 138-139, 141, 141.OV; RJ 01, 10 |
|
COCCP31 |
Condensed Occupation Code Rd 3/1 CMJ |
EM99-100; RJ 01, 01A; Constructed |
|
COCCP42 |
Condensed Occupation Code Rd 4/2 CMJ |
EM99-100; RJ 01, 01A; Constructed |
|
COCCP53 |
Condensed Occupation Code Rd 5/3 CMJ |
EM99-100; RJ 01, 01A; Constructed |
|
BGNWK31 |
Usual Start Time of Rd 3/1 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
BGNWK42 |
Usual Start Time of Rd 4/2 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
BGNWK53 |
Usual Start Time of Rd 5/3 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
ENDWK31 |
Usual End Time of Rd 3/1 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
ENDWK42 |
Usual End Time of Rd 4/2 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
ENDWK53 |
Usual End Time of Rd 5/3 CMJ |
EM 105, 105A, 105OV; RJ 01, 02 |
|
PAYVAC31 |
Paid Vacation at Rd 3/1 CMJ |
EM 1-3, 51, 109; RJ 01, 02 |
|
PAYVAC42 |
Paid Vacation at Rd 4/2 CMJ |
EM 1-3, 51, 109; RJ 01, 02 |
|
PAYVAC53 |
Paid Vacation at Rd 5/3 CMJ |
EM 1-3, 51, 109; RJ 01, 02 |
|
SICPAY31 |
Paid Sick Leave at Rd 3/1 CMJ |
EM 1-3, 51, 107; RJ 01, 02 |
|
SICPAY42 |
Paid Sick Leave at Rd 4/2 CMJ |
EM 1-3, 51, 107; RJ 01, 02 |
|
SICPAY53 |
Paid Sick Leave at Rd 5/3 CMJ |
EM 1-3, 51, 107; RJ 01, 02 |
|
PAYDR31 |
Paid Leave to Visit Dr Rd 3/1 CMJ |
EM 1-3, 51, 107-108; RJ 01, 02 |
|
PAYDR42 |
Paid Leave to Visit Dr Rd 4/2 CMJ |
EM 1-3, 51, 107-108; RJ 01, 02 |
|
PAYDR53 |
Paid Leave to Visit Dr Rd 5/3 CMJ |
EM 1-3, 51, 107-108; RJ 01, 02 |
|
RETPLN31 |
Pension Plan at Rd 3/1 CMJ |
EM 1-3, 51, 110; RJ 01, 02 |
|
RETPLN42 |
Pension Plan at Rd 4/2 CMJ |
EM 1-3, 51, 110; RJ 01, 02 |
|
RETPLN53 |
Pension Plan at Rd 5/3 CMJ |
EM 1-3, 51, 110; RJ 01, 02 |
|
SHFTWK31 |
Irregular Work Shift at Rd 3/1 CMJ |
EM 1-3, 51, 105; RJ 01, 02 |
|
SHFTWK42 |
Irregular Work Shift at Rd 4/2 CMJ |
EM 1-3, 51, 105; RJ 01, 02 |
|
SHFTWK53 |
Irregular Work Shift at Rd 5/3 CMJ |
EM 1-3, 51, 105; RJ 01, 02 |
|
BSNTY31 |
Sole Prop, Partner, Corp, Rd 3/1 CMJ |
EM 1-3, 51, 94-95; RJ 01, 02 |
|
BSNTY42 |
Sole Prop, Partner, Corp, Rd 4/2 CMJ |
EM 1-3, 51, 94-95; RJ 01, 02 |
|
BSNTY53 |
Sole Prop, Partner, Corp, Rd 5/3 CMJ |
EM 1-3, 51, 94-95; RJ 01, 02 |
|
JOBORG31 |
Priv (Profit/Nonprofit) Gov Rd 3/1 CMJ |
EM 1-3, 51, 96; RJ 01, 02 |
|
JOBORG42 |
Priv (Profit/Nonprofit) Gov Rd 4/2 CMJ |
EM 1-3, 51, 96; RJ 01, 02 |
|
JOBORG53 |
Priv (Profit/Nonprofit) Gov Rd 5/3 CMJ |
EM 1-3, 51, 96; RJ 01, 02 |
|
HELD31X |
Health Insurance Held from Rd 3/1 CMJ |
EM117; HX, HP and OE Sections |
|
HELD42X |
Health Insurance Held from Rd 4/2 CMJ |
EM117; HX, HP and OE Sections |
|
HELD53X |
Health Insurance Held from Rd 5/3 CMJ |
EM117; HX, HP and OE Sections |
|
OFFER31X |
Health Insurance Offered by Rd 3/1 CMJ |
EM113, 114, 117; RJ and HX Sections |
|
OFFER42X |
Health Insurance Offered by Rd 4/2 CMJ |
EM113, 114, 117; RJ and HX Sections |
|
OFFER53X |
Health Insurance Offered by Rd 5/3 CMJ |
EM113, 114, 117; RJ and HX Sections |
Return To Table Of Contents
HEALTH INSURANCE VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
CHmm97X |
Covered by Champus/Champva in mm 97 (Ed), where mm = JA – DE |
HX12, 13, PR19-22, HQ Section, RE14, 96A, and age at interview date |
|
MCRmm97 |
Covered by Medicare in mm 97, where mm = JA – DE |
HX05-07, 27, 29, 29OV |
|
MCRmm97X |
Covered by Medicare in mm 97 (ED), where mm = JA – DE |
HX05-07, 27, 29, 29OV, see documentation, section 2.5.8, for
additional edit specifications |
|
MCDmm97 |
Covered by Medicaid in mm 97, where mm = JA – DE |
HX10-11, PR07-10 and HQ Section |
|
MCDmm97X |
Covered by Medicaid in mm 97 (ED), where mm = JA – DE |
MCDJA97, HX14-16, 18-19, 41-43, 45, PR11-14, 23-32, 39-42 |
|
OPAmm97 |
Covered by Other Public A Ins in mm 97, where mm = JA – DE |
HX14-15, 41-45, PR 23-32 and HQ Section |
|
OPBmm97 |
Covered by Other Public B Ins in mm 97, where mm = JA – DE |
HX14-15, 41-43, PR23-30 and HQ Section |
|
STAmm97 |
Covered by Other State Prog in mm 97, where mm = JA – DE |
HX16-19, PR35-38 and HQ Section |
|
PUBmm97X |
Covered by Any Public Ins in mm 97 (ED), where mm = JA – DE |
CHJA97X, MCRJA97X,
MCDJA97X,
OPAJA97, OPBJA97 |
|
PEGmm97 |
Covered by Empl Union Ins in mm 97, where mm = JA – DE |
HX2-4, 21-24, 48; HP, OE, HQ, EM, RJ Sections |
|
PDKmm97 |
Covrd by Priv Ins (Source Unknwn) in mm 97, where mm = JA – DE |
HX21-24, 48, HP, OE, and HQ Sections |
|
PNGmm97 |
Covered by Nongroup Ins in mm 97, where mm = JA – DE |
HX21-24, 48, HP, OE, and HQ Sections |
|
POGmm97 |
Covered by Other Group Ins in mm 97, where mm = JA – DE |
HX21-24, 48, HP, OE, and HQ Sections |
|
PRSmm97 |
Covered by Self-Emp-1 Ins in mm 97, where mm = JA – DE |
HX3, 4, 48, HQ, OE, RJ and EM sections |
|
POUmm97 |
Covered by Holder Outside of RU in mm 97, where mm = JA – DE |
HX21-24, 48, HP, OE, and HQ Sections |
|
PRImm97 |
Covered by Private Ins in mm 97, where mm = JA – DE |
POGJA97, PDKJA97, PEGJA97, PRSJA97, POUJA97, PNGJA97 |
|
HPEmm97 |
Holder of Empl Union Ins in mm 97, where mm = JA – DE |
PEGJA97, HP9, 11 |
|
HPDmm97 |
Holder of Priv Ins (Source Unknwn) in mm 97, where mm = JA – DE |
PDKJA97; HP11 |
|
HPNmm97 |
Holder of Nongroup Ins in mm 97, where mm = JA – DE |
PNGJA97; HP11 |
|
HPOmm97 |
Holder of Other Group Ins in mm 97, where mm = JA – DE |
POGJA97; HP11 |
|
HPSmm97 |
Holder of Self-Emp-1 Ins in mm 97, where mm = JA – DE |
PRSJA97; HP9 |
|
HPRmm97 |
Holder of Private Insurance in mm 97, where mm = JA – DE |
HPEJA97,
HPSJA97,
HPOJA97,
HPNJA97, HRDJA97 |
|
INSmm97X |
Covrd By Hosp/Med Ins in mm 97, where mm = JA – DE (Ed) |
PUBJA97X,
PRIJA97 |
|
PRVEV97 |
Ever have private insurance during 97 |
Constructed |
|
CHPEV97 |
Ever have CHAMPUS/CHAMPVA during 97 |
Constructed |
|
MCDEV97 |
Ever have Medicaid during 97 |
Constructed |
|
MCREV97 |
Ever have Medicare during 97 |
Constructed |
|
OPAEV97 |
Ever have other public A during 97 |
Constructed |
|
OPBEV97 |
Ever have other public B during 97 |
Constructed |
|
UNINS97 |
Uninsured all of 97 |
Constructed |
|
INSCOV97 |
Health insurance coverage indicator 97 |
Constructed |
Return To Table Of Contents
HEALTH STATUS VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
RTHLTH31 |
Perceived Health Status (R3-R1) |
CE 1 |
|
RTHLTH42 |
Perceived Health Status (R4-R2) |
CE 1 |
|
RTHLTH53 |
Perceived Health Status (R5-R3) |
CE 1 |
|
RTPROX31 |
Self/Proxy Rating Of Health (R3-R1) |
CE 1OV |
|
RTPROX42 |
Self/Proxy Rating Of Health (R4-R2) |
CE 1OV |
|
RTPROX53 |
Self/Proxy Rating Of Health (R5-R3) |
CE 1OV |
|
MNHLTH31 |
Perceived Mental Health Status (R3-R1) |
CE 2 |
|
MNHLTH42 |
Perceived Mental Health Status (R4-R2) |
CE 2 |
|
MNHLTH53 |
Perceived Mental Health Status (R5-R3) |
CE 2 |
|
MNPROX31 |
Self/Proxy Rating Of Mental Health (R3-R1) |
CE 2OV |
|
MNPROX42 |
Self/Proxy Rating Of Mental Health (R4-R2) |
CE 2OV |
|
MNPROX53 |
Self/Proxy Rating Of Mental Health (R5-R3) |
CE 2OV |
|
IADLHP31 |
IADL Screener (R3-R1) |
HE 2-4 |
|
IADLHP42 |
IADL Screener (R4-R2) |
HE 2-4 |
|
IADLHP53 |
IADL Screener (R5-R3) |
HE 2-4 |
|
ADLHLP31 |
ADL Screener (R3-R1) |
HE 5-6 |
|
ADLHLP42 |
ADL Screener (R4-R2) |
HE 5-6 |
|
ADLHLP53 |
ADL Screener (R5-R3) |
HE 5-6 |
|
AIDHLP31 |
Used Assistive Devices (R3-R1) |
HE 7-8 |
|
AIDHLP53 |
Used Assistive Devices (R5-R3) |
HE 7-8 |
|
WLKLIM31 |
Limitations In Physical Functioning (R3-R1) |
HE 9-18 |
|
WLKLIM53 |
Limitations In Physical Functioning (R5-R3) |
HE 9-18 |
|
LFTDIF31 |
Difficulty Lifting 10 Pounds (R3-R1) |
HE 11 |
|
LFTDIF53 |
Difficulty Lifting 10 Pounds (R5-R3) |
HE 11 |
|
STPDIF31 |
Difficulty Walking Up 10 Steps (R3-R1) |
HE 12 |
|
STPDIF53 |
Difficulty Walking Up 10 Steps (R5-R3) |
HE 12 |
|
WLKDIF31 |
Difficulty Walking 3 Blocks (R3-R1) |
HE 13 |
|
WLKDIF53 |
Difficulty Walking 3 Blocks (R5-R3) |
HE 13 |
|
MILDIF31 |
Difficulty Walking A Mile (R3-R1) |
HE 14 |
|
MILDIF53 |
Difficulty Walking A Mile (R5-R3) |
HE 14 |
|
STNDIF31 |
Difficulty Standing 20 Minutes (R3-R1) |
HE 15 |
|
STNDIF53 |
Difficulty Standing 20 Minutes (R5-R3) |
HE 15 |
|
BENDIF31 |
Difficulty Bending/Stooping (R3-R1) |
HE 16 |
|
BENDIF53 |
Difficulty Bending/Stooping (R5-R3) |
HE 16 |
|
RCHDIF31 |
Difficulty Reaching Overhead (R3-R1) |
HE 17 |
|
RCHDIF53 |
Difficulty Reaching Overhead (R5-R3) |
HE 17 |
|
FNGRDF31 |
Difficulty Using Fingers To Grasp (R3-R1) |
HE 18 |
|
FNGRDF53 |
Difficulty Using Fingers To Grasp (R5-R3) |
HE 18 |
|
ACTLIM31 |
Any Limitation Work/Housewrk/School (R3-R1) |
HE 19-20 |
|
ACTLIM53 |
Any Limitation Work/Housewrk/School (R5-R3) |
HE 19-20 |
|
WRKLIM31 |
Work Limitation (R3-R1) |
HE 20A |
|
WRKLIM53 |
Work Limitation (R5-R3) |
HE 20A |
|
HSELIM31 |
Housework Limitation (R3-R1) |
HE 20A |
|
HSELIM53 |
Housework Limitation (R5-R3) |
HE 20A |
|
SCHLIM31 |
School Limitation (R3-R1) |
HE 20A |
|
SCHLIM53 |
School Limitation (R5-R3) |
HE 20A |
|
UNABLE31 |
Completely Unable To Do Activity (R3-R1) |
HE 21 |
|
UNABLE53 |
Completely Unable To Do Activity (R5-R3) |
HE 21 |
|
SOCLIM31 |
Social Limitations (R3-R1) |
HE 22-23 |
|
SOCLIM53 |
Social Limitations (R5-R3) |
HE 22-23 |
|
COGLIM31 |
Cognitive Limitations (R3-R1) |
HE 24-25 |
|
COGLIM53 |
Cognitive Limitations (R5-R3) |
HE 24-25 |
|
WRGLAS42 |
Wears Glasses or Contacts (R2-R4) |
HE 26-27 |
|
SEEDIF42 |
Difficulty Seeing (W/Glasses/Contacts) |
HE 28-29 |
|
BLIND42 |
Person Is Blind |
HE 30 |
|
READNW42 |
Can Read Newsprint (W/Glasses/Contacts) |
HE 31 |
|
RECPEP42 |
Can Recognize People (W/Glasses/Contacts) |
HE 32 |
|
VISION42 |
Vision Impairment (Summary) |
Constructed |
|
HEARAD42 |
Person Wears Hearing Aid |
HE 33-34 |
|
HEARDI42 |
Any Difficulty Hearing (W/Hearing Aid) |
HE 35-36 |
|
DEAF42 |
Person Is Deaf |
HE 37 |
|
HEARMO42 |
Can Hear Most Conversation |
HE 38 |
|
HEARSM42 |
Can Hear Some Conversation |
HE 39 |
|
HEARNG42 |
Hearing Impairment (Summary) |
Constructed |
|
ANYLIM97 |
Any Limitation (RD 3/1, RD 4/2 & RD 5/3) |
Constructed |
|
LIMACT42 |
Limited In Any Activities (<5 Years) |
HE 40-41 |
|
PLYLIM42 |
Limited In Play Activity (<5 Years) |
HE 42 |
|
CANTPL42 |
Can’t Participate In Usual Play (<5 Yr) |
HE 43 |
|
SPCPRO42 |
In Special Program (<5 Years) |
HE 44 |
|
DPTSHT42 |
Immunization For Dpt Shots (<7 Years) |
HE 45 |
|
NUMDPT42 |
One Or Several Dpt Shots (<7 Years) |
HE 46 |
|
POLSHT42 |
Immunization For Polio (<7 Years) |
HE 47 |
|
NUMPOL42 |
One Or Several Polio Shots (<7 Years) |
HE 48 |
|
MMRSHT42 |
Immunization For Measles/Mumps/Rubella |
HE 49 |
|
HEPSHT42 |
Immunization For Hepatitis (<7 Years) |
HE 49A |
|
MOMPRO42 |
Problem Getting Along With Mother (5-17) |
HE 50 |
|
DADPRO42 |
Problem Getting Along With Father (5-17) |
HE 50 |
|
UNHAP42 |
Problem Feeling Unhappy Or Sad (5-17) |
HE 50 |
|
SCHLBH42 |
Problem Behavior At School (5-17) |
HE 50 |
|
HAVFUN42 |
Problem Having Fun (5-17) |
HE 50 |
|
ADUPRO42 |
Problem Getting Along With Adults (5-17) |
HE 50 |
|
NERVAF42 |
Problem Feeling Nervous/Afraid (5-17) |
HE 50 |
|
SIBPRO42 |
Problem Getting Along With Sibs (5-17) |
HE 50 |
|
KIDPRO42 |
Problem Getting Along With Kids (5-17) |
HE 50 |
|
SPRPRO42 |
Problem With Sports/Hobbies (5-17) |
HE 50 |
|
SCHPRO42 |
Problem With Schoolwork (5-17) |
HE 50 |
|
HOMEBH42 |
Problem With Behavior At Home (5-17) |
HE 50 |
|
TRBLE42 |
Problem Staying Out Of Trouble |
HE 50 |
|
SPCSCH42 |
Need Special School Program (5-17) |
HE 51 |
|
SPECED42 |
In Special Education (5-17) |
HE 52 |
|
SPCHTH42 |
Received Speech Therapy (5-17) |
HE 52B |
|
PSYCNS42 |
Psychological Counseling |
HE 52B |
|
OCUPTH42 |
Received Occupational Therapy (5-17) |
HE 52B |
|
VOCSVC42 |
Received Vocational Services (5-17) |
HE 52B |
|
TUTOR42 |
Received Tutoring (5-17) |
HE 52B |
|
READIN42 |
Uses Reader Or Interpreter (5-17) |
HE 52B |
|
PHYTHR42 |
Received Physical Therapy (5-17) |
HE 52B |
|
LIFSKL42 |
Received Life Skills Training (5-17) |
HE 52B |
|
FAMCNS42 |
Received Family Counseling (5-17) |
HE 52B |
|
RECTHR42 |
Received Recreational Therapy (5-17) |
HE 52B |
|
OTHSVC42 |
Received Other School Services (5-17) |
HE 52B |
|
CANTSC42 |
Limited/Unable To Go To School (5-17) |
HE 53 |
|
LMOACT42 |
Limited In Non-School Activity (5-17) |
HE 54 |
|
HLTHY42 |
Child Resists Illness Well (0-17) |
HE 55 |
|
NTHLTH42 |
Less Healthy Than Same Age Kids (0-17) |
HE 55 |
|
GETSIC42 |
Child Catches Things Going Around (0-17) |
HE 55 |
|
HGTFT42 |
Child’s Height – Feet (0-17) |
HE 56 |
|
HGTIN42 |
Child’s Height – Inches (0-17) |
HE 56 |
|
WGTLB42 |
Child’s Weight – Pounds (0-17) |
HE 57 |
|
WGTOZ42 |
Child’s Weight – Ounces (0-17) |
HE 57 |
|
CHLIM42 |
Child Has Any Limitation (0-17) |
Constructed |
Return To Table Of Contents
WEIGHTS VARIABLES - PUBLIC USE
|
VARIABLE |
DESCRIPTION |
SOURCE |
|
WTDPER97 |
Poverty/Mortality Adj Person Weight |
Constructed |
|
WTFAMF97 |
Proverty Adjusted Family Weight |
Constructed |
|
WTCFAM97 |
Pov Adj Family Wgts-Cps Fam On 12/31/97 |
Constructed |
|
VARSTR97 |
Variance Estimation Stratum-1997 |
Constructed |
|
VARPSU97 |
Variance Estimation Psu-1997 |
Constructed |
Return To Table Of Contents
Appendix 1: Estimation Procedures in the Household Component of the 1996 Medical Expenditure Panel Survey
Steven B. Cohen
Center for Cost and Financing Studies
Agency for Healthcare Research and Quality
Ralph DiGaetano and Huseyin Goksel
Westat, Inc
The authors wish to thank Steven R. Machlin, D.E.B. Potter, and Joel W.
Cohen, Center for Cost and Financing Studies, AHRQ, for their careful reviews of
the manuscript and their insightful comments and suggested revisions.
Return To Table Of Contents
Estimation Procedures in the Household Component of the 1996 Medical
Expenditure Panel Survey
Steven
B. Cohen, AHCPR, Ralph DiGaetano and Huseyin Goksel, Westat
1.0 Introduction
The Household Component of the 1996 Medical Expenditure Panel
Survey (MEPS) was designed to produce national and regional estimates of the
health care utilization, expenditures, sources of payment and insurance coverage
of the U.S. civilian non-institutionalized population for calendar year 1996.
The MEPS includes surveys of medical providers, employers and other health
insurance providers to supplement the data provided by household respondents.
The design of the MEPS survey permits both person based and family level
estimates. The scope and depth of this data collection effort reflects the needs
of government agencies, legislative bodies, and health professionals for the
comprehensive national estimates needed in the formulation and analysis of
national health policies. It is the third in a series of national probability
surveys conducted by the Agency for Health Care Policy and Research (AHCPR) on
the financing and utilization of medical care in the United States. Prior
surveys include the 1977 National Medical Care Expenditure Survey (NMCES) and
the 1987 National Medical Expenditure Survey (NMES).
The Medical Expenditure Panel Survey (MEPS) household
component is an ongoing annual survey, with each sample panel collecting data
over a 30 month period to obtain information that covers two consecutive
calendar years. The MEPS collects data on the specific health services that
Americans use, how frequently they use them, the cost of these services and how
they are paid, as well as data on the cost, scope, and breadth of private health
insurance held by and available to the U.S. population. MEPS is unparalleled for
the degree of detail in its data, as well as its ability to link health service
medical expenditures and health insurance data to the demographic, employment,
economic, health status, utilization of health services, and other
characteristics of survey respondents. Moreover, MEPS is the only federally
sponsored national survey that provides a foundation for estimating the impact
of changes in sources of payment and insurance coverage on different economic
groups or special populations of interest, such as the poor, elderly families,
veterans, the uninsured, and racial and ethnic minorities. The survey is
co-sponsored by the Agency for Health Care Policy and Research and the National
Center for Health Statistics. Westat and the National Opinion Research Center
(NORC) are the data collection organizations for the 1996 MEPS Household Survey.
The sample design of the household component of the MEPS can
be characterized as a stratified multi-stage area probability design with
disproportionate sampling to facilitate the selection of an oversample of
minorities (Cohen, 1997). This report provides a detailed summary of sample
yields for the three rounds of data collection that cover calendar year 1996. An
overview is also provided of the weighting strategies adopted to obtain national
estimates of health care parameters for the U.S. civilian non-institutionalized
population. In addition, survey design complexities which require special
consideration for variance estimation and analysis are discussed. Return To Table Of Contents
2.0 The MEPS Household Component
The set of households selected for the 1996 MEPS is a
subsample of those participating in the National Health Interview Survey (NHIS).
The NHIS is an on-going annual household survey of approximately 42,000
households (109,000 individuals) conducted by the National Center for Health
Statistics to obtain national estimates for the U.S. civilian
non-institutionalized population on health care utilization, health conditions,
health status, insurance coverage and access. In addition to the cost savings
achieved by eliminating the need to independently list and screen households,
selecting a subsample of NHIS participants has resulted in an enhancement in
analytical capacity of the resultant survey data. Use of the 1995 NHIS data in
concert with the data collected for the 1996 MEPS provides an additional
capacity for longitudinal analyses not otherwise available. Furthermore, the
greater number and dispersion of the primary sampling units (PSUs) that comprise
the MEPS national sample has resulted in improvements in precision over prior
expenditure survey designs (Arnett et al., 1996; Cohen, 1996).
The MEPS Household Component (HC) consists of an overlapping
panel design in which any given sample panel is interviewed a total of 5 times
over 30 months to yield annual use and expenditure data for two calendar years.
Design specifications for the 1996 MEPS required that the full series of
interviews necessary to acquire calendar year information for 1996 should be
completed in approximately 9,000 households. The same panel of households were
interviewed in person three times over the course of the survey to obtain data
on their health care experience for 1996 (J. Cohen, 1997).
The 1996 MEPS Household Component sample was selected from
households that responded to the 1995 National Health Interview Survey (NHIS).
More specifically, the 1996 MEPS Household sample linked to the 1995 NHIS was
selected from a nationally representative NHIS sub-sample from 2 NHIS panels out
of 4 to represent the nation, and encompassed half of the participating
households in the NHIS sample during the second and third quarters of 1995. It
should be noted that the NHIS has been designed to permit nationally
representative subsamples to be selected by restricting the sample to one of
four distinct panels. Any combination of 1 to 4 panels will provide a nationally
representative sample of households. Furthermore, each NHIS panel subsample for
a given quarter of a calendar year is nationally representative.
The complete 1995 NHIS sample (panels 1-4) consists of 358
primary sampling units (PSUs: counties or groups of contiguous counties) with a
targeted sample of approximately 42,000 responding households. The sample PSUs
selected for the NHIS were stratified by geographic area (Census region and
state), metropolitan statistical area, and socio-demographic measures (Judkins,
Marker and Waksberg, 1994). Within sample PSUs, a sample of blocks (segments)
were selected after being stratified by measures of minority population density,
used to oversample areas with high population concentrations of blacks and
Hispanics. A nationally representative sample of approximately 71,000 addresses
within sampled blocks was selected and targeted for further screening to include
an oversample of household containing blacks and Hispanics as part of the 1995
NHIS interview. Return To Table Of Contents
The nationally representative 1995 NHIS subsample selected
for the 1996 MEPS consists of 195 PSUs, and in the two targeted quarters of 1995
these PSUs include 1,675 sample segments (second stage sampling units) and
10,597 responding NHIS households. This NHIS sample reflects an over-sample of
households with Hispanics and blacks at the following approximate ratios of
representation relative to the remaining households (Hispanics 2.0:1, blacks
1.5:1). The sample size for the 1996 MEPS was targeted at approximately 9,000
reporting units (generally families or single persons) yielding the complete
series of core interviews (i.e., Rounds 1-3) to obtain use and expenditure data
for calendar year 1996.
2.1 Procedures for Data Collection and MEPS Sampling Unit
Definitions
Five in person interviews were conducted with each NHIS panel
selected for the MEPS at three- to four-month intervals over an approximately
30-month field period. The first three of these rounds (Rounds 1-3) defined the
1996 MEPS Household survey, and serve to collect the main body of annual
utilization and expenditure data for calendar year 1996. Rounds 3-5 for the 1996
MEPS panel cover 1997 and will be combined with Rounds 1-3 of the 1997 MEPS
panel to yield the full sample base for the 1997 MEPS household survey and the
source of annual estimates for that calendar year. All interviews were conducted
in person using a computer assisted personal interview (CAPI) as the principal
data collection mode. Round 1 asks about the period since January 1 of the MEPS
year to the date of that interview; Round 2 asks about the time since the Round
1 interview through the date of the Round 2 interview; and Round 3 collects data
from the date of the Round 2 interview in 1996 through the date of the Round 3
interview in 1997. Thus, Round 3 covers both calendar years, and the data are
partitioned accordingly for estimation purposes.
The definitions for Dwelling Units and Group Quarters in the
MEPS Household Component are generally consistent with the definitions employed
for the National Health Interview Survey. While the MEPS sample is a subsample
of NHIS dwelling units (referred to as households), a reporting unit for MEPS
data collection purposes was defined as a person or group of persons in a
sampled dwelling unit that are related by blood, marriage, adoption or other
family associations, who were to be interviewed at the same time. Therefore,
when unrelated persons were living in the same dwelling unit, sample households
were split into multiple reporting units. Examples of the relationship between
sample dwelling units and corresponding reporting units are:
1. A married daughter and her husband living with her parents
in the same dwelling are considered one reporting unit.
2. A husband and wife and their unmarried daughter, age 18,
who is living away from home at college constitute two reporting units
operationally (though only one family unit analytically).
3. Three unrelated persons living in the same dwelling unit
represent three reporting units.
In the first round of the 1996 MEPS, there was an average of
1.09 reporting units per sample dwelling unit. This low average reflects the
fact that a substantial proportion of sample dwelling units contained only one
reporting unit.
In MEPS, analyses are conducted at both the individual and
family levels. Through the reenumeration section of the Round 1 questionnaire,
the status of each individual sampled at the time of the NHIS interview is
classified as "key or non-key" and "inscope or
out-of-scope". The "keyness" and "scope" indicators,
together, define the target sample to be used for person level national
estimates. They are discussed in detail below.
Return To Table Of Contents
Inscope Persons: An individual is inscope whenever the
person is a member of the civilian non-institutionalized population. Because a
person’s eligibility for the survey may have changed since the NHIS interview,
sampling reenumeration takes place in each subsequent reinterview for persons in
all households selected into the core survey.
Key Persons: A "key" survey participant is one
whose chance of selection for MEPS is linked to the sample of households
originally selected for the NHIS (college students interviewed in dorms for the
NHIS are not included in MEPS; college students living away from home are
included in MEPS when identified by their parents during MEPS enumeration as
living away from home as the students usual place of residence). A person must
be key in order to be eligible to receive a person level weight (other
conditions must be met as well).
Key survey participants include all civilian
non-institutionalized individuals who resided in households that responded to
the nationally representative NHIS subsample reserved for the MEPS. Members of
the armed forces that are on full time active duty and reside in responding NHIS
households, which include other family members who are civilian
non-institutionalized individuals, are also considered key persons. However,
they are considered out of scope for person level estimates derived for the
survey unless they re-enter the civilian non-institutionalized population for
some time during 1996.
Individuals who join the NHIS reporting units that define the
1996 MEPS household sample (in Round 1 or later MEPS rounds) and did not have an
opportunity for selection during the time of the NHIS interview will also be
considered key persons. These include newborns, individuals who were in an
institution or outside the country moving to the United States, and military
personnel previously residing on military bases who join MEPS reporting units to
live in the community.
College students under 24 years of age interviewed at
dormitories in the 1995 NHIS were considered ineligible for the 1996 MEPS sample
and not included in that sample. Furthermore, any unmarried college students
under 24 years of age who responded to the 1995 NHIS interview while living away
at school (not in a dormitory) were excluded from the sample if it was
determined in the MEPS Round 1 interview that the person was unmarried, under 24
years of age, and a student with parents living elsewhere who resided at his/her
current housing only during the school year. If, on the other hand, the person’s
status at the time of the MEPS Round 1 interview was no longer that of an
unmarried student under 24 years of age living away from home, then the person
was retained in the 1996 MEPS sample as a key person.
Alternatively, at the time of the MEPS Round 1 interview with
NHIS sample respondents, a question was asked to determine if there are any
related college students under 24 years of age who usually live in the sampled
household, but are currently living away from home and going to school. These
college students were considered key persons and were identified and interviewed
at their college address, but linked to the sampled household for family
analyses. Some of these college students living away from home at the time of
the Round 1 interview were identified as living in sampled household at the time
of the 1995 NHIS interview. The remainder were identified at the time of the
MEPS Round 1 interview with the NHIS sampled households.
Non-key Persons: Persons who were not living in the
original sampled dwelling unit at the time of the 1995 NHIS interview and
where part of the civilian non-institutionalized population at that time will be
considered non-key. If such persons happen to be living in a MEPS sampled
household in Round 1 or later rounds, MEPS data, (e.g., utilization and income)
will be collected for the period of time they are part of the sampled unit to
permit family analyses. Non-key persons who leave a sample family without an
accompanying key, inscope person will not be recontacted for subsequent
interviews. Non-key individuals are not part of the target sample used to obtain
person level national estimates.
In situations where key inscope MEPS participants move out
(in Round 1 or later rounds) and join or create another family, data on all
members who are related by blood, marriage, adoption or foster care to the key
inscope MEPS participants will also be obtained from the point in time that the
key inscope person(s) joined the family. Similarly, data will be collected (in
Round 1 and later rounds) on all related persons who join families already
participating in MEPS, whether the new persons are key or nonkey.
Key, inscope MEPS participants who entered a nursing home,
thus leaving the civilian, non-institutionalized population of the United
States, also had data collected during their stay in the nursing home. All other
key inscope persons who left the civilian, non-institutionalized population of
the United States did not require any data collection for this period. Upon
their return to the U.S. civilian noninstitutional population, these persons
were once again subject to data collection in MEPS.
Eligible Persons: A person is eligible for data
collection in MEPS if they are key and inscope. In addition, individuals who are
nonkey and inscope and a member of a family with at least one member who is key
and inscope are also eligible for data collection. Out of scope individuals who
are full time active duty members of the armed forces are also eligible for MEPS
data collection for the time period they are a member of a family with at least
one member who is key and inscope.
Return To Table Of Contents
3.0 MEPS Round 1 Field Results
The 1995 NHIS subsample eligible for the 1996 MEPS consisted
of 10,639 responding NHIS dwelling units. Of these, 10,597 had sufficient
information to permit MEPS data collection (99.6 percent). Table 1 summarizes
response rates for MEPS (conditional on response to NHIS) at both the dwelling
unit and reporting unit levels. The 10,509 sample dwelling units that had
sufficient address information from the NHIS and were considered eligible for
MEPS contained a total of 11,424 reporting units. Of these reporting units, 83.1
percent responded to the first MEPS interview, 2.2 percent could not be located,
and 14.7 percent were located but did not participate in the MEPS interview.
In order for a reporting unit to be eligible for MEPS data
collection, it had to include at least one "key" individual selected
in the MEPS, who was a member of the civilian non-institutionalized population
between 1/1/96 and the date of the MEPS interview. Within the 10,597 sampled
dwelling units that constitute the MEPS Round 1 sample, 11,590 reporting units
were identified and targeted for data collection. Of these, 166 reporting units
were determined to be ineligible for the 1996 MEPS. MEPS sample ineligibility
for Round 1 was a consequence of the following situations:
- All members of the reporting unit died prior to 1/1/96 (21);
- All members of the reporting unit were full time active duty members of
the military prior to 1/1/96 (4);
- All members of the reporting unit were institutionalized prior to 1/1/96
(26);
- All members of the reporting unit left the U.S. prior to 1/1/96 (29);
- All members of the reporting unit ineligible for data collection (e.g.
death and inst.) (86).
Of the 11,424 eligible reporting units targeted for
interviews in Round 1, 9,488 responded to the first core MEPS interview (83.1
percent, Table 1). The remaining 1,936 eligible reporting units (16.9 percent)
were classified nonrespondents due to the following reasons:
- refusal to complete the interview (1,506);
- unavailable during field period (43);
Since the MEPS sample is a nationally representative
sub-sample of households that were part of the 1995 NHIS, the response rate that
has implications in the development of national estimates from MEPS is a
function of the response rates to both surveys. Specifically, the overall Round
1 MEPS response rate can be derived as the product of the following three
components:
1. the NHIS response rate achieved for the households
eligible for the MEPS (93.9 percent)
2. the proportion of NHIS units selected that had
sufficient information to permit inclusion in the MEPS data collection
effort (99.6 percent)
3.
the MEPS round 1 reporting unit conditional response rate (83.1 percent).
The combination of these factors resulted in a response rate
of 77.7 percent (.939 x .996 x .831) for the 1996 MEPS Round 1 HC (Cohen and
Machlin, 1998).
Table 1: Response Rates For 1996 MEPS Round 1
| |
Dwelling Units |
Reporting Units |
| |
Number |
Percent |
Number |
Percent |
|
Sample Cases |
10,597 |
-- |
11,590 |
-- |
|
Sample Eligibles |
10,509 |
100.0 |
11,424 |
100.0 |
|
Respondents |
8,793 |
83.7 |
9,488 |
83.1 |
|
Nonrespondents |
1,716 |
16.3 |
1,936 |
16.9 |
|
Unable to Locate |
|
|
251 |
2.2 |
|
Nonparticipants |
|
|
1685 |
14.7 |
Note: Conditional on NHIS Response.
In Table 1, the conditional response rates for the 1996 MEPS
Round 1 survey are shown at both the dwelling unit level and at the reporting
unit level. Since there is generally a one-to-one correspondence between a
dwelling unit and a reporting unit, the conditional response rates for both are
very similar (83.7 vs. 83.1 percent, respectively). While the reporting unit
level response rate is more meaningful from an operational perspective, the
dwelling unit level response rate is also provided because it is at this level
that the MEPS estimation weights are initially adjusted for nonresponse.
Return To Table Of Contents
4.0 MEPS Sampling Weight Specifications
Due to the complex design of the MEPS Household Component,
the MEPS sample data must be appropriately weighted to obtain approximately
unbiased national estimates for the U.S. civilian non-institutionalized
population. The sampling weights developed for this purpose reflect the
disproportionate sampling adopted in the NHIS to oversample minority populations
in addition to adjustments for the following:
- Complete nonresponse of eligible sample units
- Partial response of survey participants providing data for only a portion
of the time in 1996 during which they were eligible to respond
- Poststratification to more accurate population totals obtained from the
Current Population Survey
The 1996 MEPS estimation weights are built from the
estimation weights developed for the 1995 National Health Interview Survey. To
reduce the impact of large sampling weights on resultant variances of survey
estimates, the MEPS estimation weights reflect a weight trimming adjustment. The
1996 MEPS dwelling unit weights also include an initial ratio adjustment to
population estimates for selected socio-economic measures derived from the full
1995 National Health Interview Survey and subsequent adjustments for nonresponse
to the first round of the MEPS survey. In addition, the MEPS estimation weights
developed at the person and family level reflect additional adjustments that
poststratify the MEPS survey estimates to more accurate population totals
obtained from the Current Population Survey. The details of the MEPS estimation
weights development are described in this section.
Return To Table Of Contents
4.1 Base weights for the 1996 MEPS
As a consequence of the survey linkage between the 1995 NHIS
and the MEPS, the sampling weights developed for the NHIS serve as the base
weights for the 1996 MEPS. More specifically, the base weight for the dwelling
units selected in the 1996 MEPS is the nonresponse adjusted 1995 NHIS
quarter-specific estimation weight of the reference person in the primary
reporting unit of a sampled dwelling unit. The reference person is the person
who owns or rents the house. This NHIS estimation weight reflects the household’s
probability for selection in the NHIS and adjustments for NHIS survey
nonresponse.
More specifically, if
P(I) is the ith dwelling unit’s
probability of selection in the NHIS to represent the Qth
Quarter of 1995, and includes disproportionate values associated with
the oversampling of minorities, and
A(c) adjusts for NHIS nonresponse within nonresponse
adjustment class c of which dwelling unit I is a member, then the NHIS
estimation weight NHISWTQ(I), for the ith dwelling unit
selected for the MEPS in quarter Q=2 or 3 would take the form
NHISWTQ(I) = (1/P(I)) * A(c)
The NHIS quarter specific base weight was obtained by using
the final quarter basic NHIS weight on the 1995 NHIS analytical file delivered
to AHCPR. The available estimation weight also included a first-stage ratio
adjustment that adjusts the initial NHIS population estimates to Census
estimates for cross-classification of the population based on race/ethnicity
(Hispanic, nonHispanic Black, other), Census region (East, Midwest, South and
west) and MSA classification (MSA/nonMSA). This component needed to be factored
out of the NHIS estimation weight, since the first-stage ratio adjustment was
implemented in NHIS without reflecting the subsampling of NHIS PSUs for MEPS
which occurred by MSA classification. Consequently, the initial MEPS base weight
was specified as
WT.MEP.I = HIS.WT.BF/HIS.ADJ.
Use of the NHIS quarter-specific estimation weight across
multiple quarters of 1995 to produce a national estimate required a division of
the weight by the number of quarters being pooled. Since the MEPS sample was
confined to quarters 2 and 3 of calendar year 1995, the NHIS quarter weight,
HIS.WT.BF was initially divided by 2, HIS.WT.BF/2 . Since the MEPS sample was
restricted to Panels 1 and 3 out of a 4 Panel NHIS design, it represented a 50
percent subsample of the NHIS. Consequently, the NHIS quarter weight,
HIS.WT.BF/2, representing Quarters 2 and 3 needed to be further multiplied by 2
to reflect the 50 percent subsample considered for MEPS. Consequently,
specification of the initial MEPS base weight as
WT.MEP.I = HIS.WT.BF/HIS.ADJ
reflects the restriction of the NHIS sample to quarters 2 and
3 and a 50 percent sample for the 1996 MEPS.
As mentioned previously, unmarried students between the ages
of 17-23 living at dormitories who were respondents in the 1995 NHIS were not
eligible for the 1996 MEPS. Furthermore, a very small set of NHIS dwelling units
(54) that were determined to be eligible for the MEPS at the time of sample
selection could not be linked back to the 1995 NHIS analytical file that was
provided a year later. The following strategy was implemented to obtain a base
weight for these dwelling units. Median values of WT.MEP.I were determined for
the dwelling units eligible for MEPS that linked back to the NHIS analytical
file, based on classes defined by a cross classification of the minority status
of the dwelling unit (1. DU has a Hispanic or black member, 2 otherwise) and 20
mutually exclusive and exhaustive distinct sampling strata defined for NHIS at
the segment level for oversampling purposes. MEPS base weight assignments for
the nonlinked cases were made based on the median value of WT.MEP.I for the
class with which they were associated. Return To Table Of Contents
4.2 Trimming MEPS Base Weights
An initial examination of the distribution of the MEPS base
weights identified a high level of variability. To correct for the impact of
large sampling weights on resultant MEPS variance estimates, the initial MEPS
base weights were trimmed according to the following specifications:
In each of the 40 classes (c) determined by a
cross-classification of the dwelling unit’s minority status and the 20 NHIS
sampling strata defined at the segment level for oversampling purposes, the mean
of the initial MEPS base weight, MEANDUWT(c) = MEAN(WT.MEP.I(i is an element
of c)) was computed. For the dwelling units within a given class c, if the initial
MEPS base weight was greater than 3 times the mean of the base weights, the
weight was truncated to that value. Otherwise, they retained their initial
value. More specifically, for class c, where c= 1,..40,
IF WT.MEP.I(I) >3*MEANDUWT(c), then
TRIMFAC = 3* (MEANDUWT(c)/ WT.MEP.I(I));
IF WT.MEP.I(I) < 3*MEANDUWT(c)
then TRIMFAC = 1
Consequently, the trimmed MEPS weights were specified as
TRIMDUWT(I) = TRIMFAC*WT.MEP.I(I).
The sum of the initial MEPS base weights, reflecting an
adjustment for NHIS nonresponse, but no correction for undercoverage was
90,754,892. Subsequent to the trimming adjustment, the sum of the MEPS base
weights at the dwelling unit level was 90,647,643. While only a few sampling
weights were modified, as can be noted in the modest reduction in the sum of the
sampling weights, the largest MEPS base weight was reduced by nearly 50 percent. Return To Table Of Contents
4.3 Ratio Adjustment of the Trimmed MEPS Base Weights
To improve the accuracy of the MEPS estimates, the trimmed
dwelling unit weights were subsequently ratio-adjusted to population estimates
derived from the full 1995 NHIS, using data from the first 3 quarters of the
1995 NHIS (all of the 1995 NHIS that was available at the time of MEPS sampling
weights development). The following measures were used in the specification of
the ratio adjustment cells to facilitate the adjustment at the dwelling unit
level:
1. MSA Status (MSA: Central City, MSA: Not Central City,
Non-MSA)
2. Family Income classification of reference person
(Below Poverty, Under $35,000 but above poverty, Equal or greater than
$35,000, Unknown)
3. Employment status of reference person (employed,
unemployed or not in labor force)
4. Race/Ethnicity of reference person (Hispanic, black
Non-Hispanic, other)
5. Dwelling unit level measure of activity limitations
(At least 1 person in DU either can’t perform major activity or is limited
in kind and amount in major or other activities, No member in DU has an
activity limitation).
These measures were selected to represent a set of measures
that related to the oversampling done in NHIS (DU minority status and MSA
status), and socio-economic and health specific measures potentially associated
with health care use, expenditure and insurance coverage behavior that would not
be used to define the family and person level poststratification adjustments in
MEPS. For dwelling units associated with more than one reporting unit, the
reference person and family income of the primary reporting unit were used for
classification purposes. Cross-classification of these measures yielded 144
weighting class cells to implement the ratio adjustment to more accurate
national estimates at the household level based on the entire 1995 NHIS sample
for quarters 1-3.
More specifically, the DU-level ratio adjustment for the c-th
weighting class takes the form
where ie c represents all NHIS
dwelling units in c selected for the 1996 MEPS , TRIMDUWT(I) represents the
trimmed initial NHIS base weight for the ith dwelling unit selected
for MEPS, NHISDU(c) represents the national population estimate at the dwelling
unit level for weighting class c, derived from the 1995 NHIS, using data from
Quarters 1-3. Consequently, the ratio adjusted MEPS dwelling unit weight
DUPSWT(I), for the ith dwelling unit associated with class c,
adjusted to population estimates derived from the full 1995 NHIS, takes form:
DUPSWT(I) = A( c ) x TRIMDUWT(I).
The sum of the ratio adjusted and trimmed MEPS dwelling unit
weights was 104,002,800 for the 10,597 NHIS dwelling units fielded for the 1996
MEPS.
Return To Table Of Contents
4.4 MEPS Nonresponse Adjusted Dwelling Unit Weights: Round 1
Of the 10,509 dwelling units eligible for data collection in
the first Round of the 1996 MEPS, 8,793 (83.7 percent) contained at least one
reporting unit that responded to the MEPS interview. Since survey nonresponse is
potentially a significant source of bias in survey estimates, the MEPS dwelling
unit sampling weights included an adjustment for survey nonresponse to help
reduce the potential for bias due to survey nonresponse. In general, the greater
the difference among subgroups in response rates and the analytic
characteristic(s) of interest, the greater the need to adjust survey weights for
nonresponse. In the MEPS, a weighting class nonresponse adjustment was
implemented, under the assumption that nonresponding sampling units would have
responded in a similar manner as respondents with similar socio-demographic and
economic characteristics within the same adjustment class. Properly designed, a
weighting class nonresponse adjustment strategy can result in a reduction in
nonresponse bias. The technique requires a partitioning of the sample into
mutually exclusive classes, with classification information available for both
responding and nonresponding units (Cox and Cohen, 1985).
Analyses of characteristics associated with differential
nonresponse in MEPS were conducted to identify the most important measures to
employ in the development of a nonresponse adjustment to the MEPS sampling
weights to correct for potential nonresponse bias at the dwelling unit level
(DiGaetano and Goksel, 1996; Cohen and Machlin, 1997). To facilitate these
comparisons, the demographic, socio-economic, health related and interview
specific profiles of respondents and nonrespondents were examined, based on
available data for both groups from the 1995 National Health Interview Survey.
Based on the results of these analyses, weighting classes
were specified for the MEPS Round 1 dwelling unit nonresponse adjustments,
defined by cross-classifications of the following measures:
- Family income of primary reporting unit (<10K, 10-19K, 20-34K, 35K+,
unknown)
- Size of dwelling unit (1,2,3,4,5+)
- MSA size (MSA-population 500K+; MSA- population under 500K; non-MSA)
- Region (Northeast, Midwest, South, West)
- Employment classification of reference person (Gov’t, private sector,
not in labor force/never worked/worked without pay, unknown or <18)
- DU level personal help measure (at least one member unable to perform
personal care activities or other routine needs; remaining units with person
70 or older; remaining units with no limitations)
- Propensity to cooperate: Phone number provided during NHIS (phone number
provided, phone with no number provided, no phone, unknown)
- Age of reference person (<24, 25-34, 35-44, 45-64, 65+)
- Race/ethnicity of reference person (Hispanic, black/nonHispanic, other)
- Marital status (married-spouse present, other)
Overall, 49 cells were identified based on
cross-classifications of these measures with cell collapsing specified according
to a hierarchy determined by significance level. The reference person was
defined as the person within the dwelling unit who owns or rents the sampled
residence.
More specifically, the nonresponse adjustment for the c-th weighting class takes the form:
where DUPSWT(I) is the initial MEPS Round 1 dwelling unit
weight for the ith sample dwelling unit, which reflects the
reciprocal of the dwelling unit’s selection probability for MEPS and a
poststratification adjustment to 1995 NHIS population totals,
E(I)=1 for all eligible MEPS dwelling units, E(I)=0
otherwise;
R(I)=1 for all eligible MEPS dwelling units responding in
Round 1, R(I)=0 otherwise;
and I e c represents eligible
dwelling units classified in weighting class c.
Consequently, the estimation weight adjusted for MEPS Round 1
dwelling unit nonresponse, WGTDU1(I), for the ith dwelling unit
associated with class c, takes the form:
WGTDU1(I) = B( c ) x DUPSWT(I).
The sum of the nonresponse adjusted MEPS dwelling unit
weights was 102,892,600 for the 8,793 eligible dwelling units with at least one
responding reporting unit in Round 1 of the MEPS. Return To Table Of Contents
4.5 MEPS Family Level Estimation Weights: Round 1
In MEPS, a family was defined as a person or group of persons
who are living together and are related by blood, marriage (or partnerships that
are viewed as such), adoption or other family associations. Any related college
students under 24 years of age who usually live in the sampled household, but
are currently living away from home and going to school full time are considered
to be members of the family. These college students are considered key persons
in MEPS and are interviewed at their college address, but linked to the sampled
household for family analyses. Families in MEPS without college students living
away from home were identified as single reporting units. Families in MEPS with
college students living away from home were identified by linking the student
reporting unit(s) back to their parent(s) reporting unit.
In order to be considered a responding family in MEPS for the
Round 1 interview, the family needed to include at least one person who was key,
inscope and eligible for data collection. Furthermore, all such key, inscope and
eligible persons had to have responded for their entire period of eligibility in
1996 covered by the Round 1 interview. Each family in MEPS characterized as
responding was assigned the weight of its corresponding dwelling unit that had
been adjusted for nonresponse:
WGTFAM(I) = WGTDU1(I)
Overall, 9,488 reporting units responded to the first round
of the MEPS, which translated to 9,388 responding families after linking the
responding student reporting units back to their parent(s) family.
The initial weights at the family level were then further
poststratified to reflect population estimates obtained from the March 1996
Current Population Survey for unrelated individuals plus families. This
poststratification also served as an adjustment for nonresponse at the family
level. The weighting classes that were considered for the family level
poststratification adjustment were defined by a cross-classification of the
following variables defined at the time of the MEPS Round 1 interview:
- Family type: reference person married (oldest person when there is no
reference person) and spouse present, male reference person and spouse not
present, female reference person and spouse not present;
- Race/ethnicity of reference person (oldest person when there is no
reference person) in family: Hispanic, Black-nonHispanic, Other-nonHispanic;
- Region: Northeast, Midwest, South and West;
- Metropolitan Statistical Area status: MSA, Non-MSA:
- Number of persons in family: 1, 2, 3, 4, 5+;
- Age of reference person (oldest person when there is no reference person)
in family: <35, 35-44, 45-64, 65+.
More specifically, the family level poststratification
adjustment for the c-th weighting class takes the form:
where CPSFAM(c) represents the national
population estimate at the family level for weighting class c, derived from the
March 1996 Current Population Survey, ie c represents
all MEPS family units classified in c that responded to the Round 1 interview,
and WGTFAM(I) represents the initial MEPS family level weight for the ith
family unit responding in the 1996 MEPS. Consequently, the Round 1
poststratified MEPS family unit weight WGTRU1(I), for the ith
family unit associated with class c, adjusted to population estimates derived
from the March 1996 Current Population Survey, takes the form:
WGTRU1(I) = C(c) x WGTFAM(I).
The weighted estimate of the number of family units
(including single person units) containing at least one member of the U.S.
civilian non-institutionalized population is 110,206,950. It is obtained by
summing the poststratified MEPS family unit weights for the 9,388 MEPS family
units that responded to the Round 1 interview. In the development of family
level attributes in MEPS, it should be noted that all eligible and responding
persons who are inscope, consisting of both key and nonkey individuals, should
be included when deriving family level estimates. Return To Table Of Contents
4.6 MEPS Person Level Estimation Weights: Round 1
Key, inscope MEPS survey participants in a responding Round 1
reporting unit, for whom data were obtained for their entire Round 1 period of
eligibility in 1996, were assigned estimation weights.
In order to be considered a responding survey participant in
MEPS for the Round 1 interview, the person needed to be in scope with data
provided for their entire Round 1 period of eligibility in 1996. All key,
inscope and eligible sample participants in MEPS that satisfied this criterion
for survey response were assigned estimation weights. The initial person level
estimation weight assigned to these MEPS survey respondents was the
corresponding poststratified family unit estimation of which they were a member,
WGTPER(I) = WGTRU1(I)
Overall, 23,612 key, inscope and eligible individuals were
classified as survey respondents in the first round of the MEPS. The Round 1
MEPS person level weights were then poststratified to population totals obtained
from the March 1996 Current Population Survey.
To establish consistency between family level and person
level estimates in the MEPS, the reference person for each family (oldest person
when there is no reference person), in addition to married couples living
together, retained the value of the MEPS family unit weight as their final
person weight:
WGTSP1(I) = WGTRU1(I)
The person level estimation weights of all other MEPS key,
inscope and eligible survey respondents (e.g. child of reference person) were
poststratified to population totals obtained from the March 1996 CPS within
weighting classes defined by a cross-classification of the following variables:
- Region: Northeast, Midwest, South and West;
- Race/ethnicity: Hispanic, Black-nonHispanic, Other-nonHispanic;
- Sex: Male, Female;
- Age at interview date: <1, 1-4, 5-9, 10-14, 15-19, 20-29, 30-34, 35-44,
45-54, 55-59, 60-64, 65-69, 70-74, 75-79, 80+.
This adjustment served as both a nonresponse and
poststratification adjustment at the person level.
The person level poststratification adjustment factor for the
c-th weighting class takes the form
D(c)= 1
for the reference person for each family (oldest person when
there is no reference person), in addition to married couples living together
(denoted by L(I) = 1; L(I) = 0 otherwise) and for others, this takes the
form
where CPSPER(c) represents the national
population estimate at the person level for weighting class c, derived from the
March 1996 Current Population Survey, ie c represents
all MEPS key and inscope survey participants classified in c that responded to
the Round 1 interview, and WGTPER(I) represents the initial MEPS person
level weight for the ith person responding in the 1996 MEPS.
Consequently, the Round 1 poststratified MEPS person weight WGTSP1(I),
for the ith person associated with class c, adjusted to population
estimates derived from the March 1996 Current Population Survey, takes the form:
WGTSP1(I) = D(c) x WGTPER(I).
The weighted estimate of the number of persons who are
members of the U.S. civilian non-institutionalized population as of the Spring
of 1996 is 263,515,813. It can be derived by summing the poststratified MEPS
person weights for the 23,612 MEPS key and inscope survey participants
classified as respondents for the Round 1 interview , as indicated on the MEPS
Household Component Public Use File HC-001:1996 Panel, Round 1 Population
Characteristics.
Return To Table Of Contents
4.7 MEPS Full Year 1996 Person Level Estimation Weights: Part-Year Nonresponse Adjustment
The MEPS Round 1 person level weight was developed to make
estimates of the health care experience and insurance coverage profiles of the
civilian non-institutionalized population for the first half of 1996. In order
to facilitate the derivation of person level estimates that cover all of
calendar year 1996, an annual person level weight for 1996 was also developed.
Application of this weight will permit the derivation of national estimates of
the health care use, expenditures, insurance coverage and sources of payment
profiles for the civilian non-institutionalized population for calendar year
1996.
In order to be considered a responding survey participant in
MEPS for the purpose of deriving annual 1996 estimates, the person had to be key
and inscope with data provided for their entire period of eligibility in 1996.
If all the key, inscope and eligible sample participants in MEPS with positive
values for the MEPS Round 1 person level weight, in addition to new key and
inscope respondents who joined a responding household in 1996 after Round 1
(here, the new respondent acquiring the sampling weight of the family they
joined), responded for their entire period of eligibility in 1996, no additional
adjustment for part year survey nonresponse over the course of Rounds 1-3 would
be necessary. Of 23,881 sample participants identified in MEPS, 21,571 or 90.33
percent provided data for their entire period of eligibility in 1996.
Consequently, the overall MEPS person level response rate for deriving annual
estimates was 70.2 percent (.777 x .903), after factoring in the impact of
survey attrition.
Since survey nonresponse is potentially a significant source
of error or bias in survey estimates, the MEPS full year sampling weights
included an adjustment for survey attrition to help reduce the potential impact
of bias. An analysis of the characteristics that distinguish MEPS respondents
with survey response for their entire period of eligibility in 1996, relative to
the Round 1 participants that discontinued survey participation, was conducted
to identify the most important variables to incorporate into the nonresponse
adjustments to the MEPS sampling weights to correct for part-year survey
nonresponse. This analysis was based on data from the first two rounds of the
survey, due to the unavailability of relevant Round 3 data for 1996 at the time
of this analysis. The results of a logistic regression analysis identified the
most important measures to include in the specification of a nonresponse
adjustment to the MEPS sampling weights to correct for part-year response for
calendar 1996 at the person level. Based on the results of these analyses,
weighting classes were specified for the MEPS full year person level nonresponse
adjustments, defined by cross-classifications of the following measures as of
Round 1, or the first eligible Round in MEPS for key and inscope respondents who
joined a household after Round 1 :
- Round 1 Interview Classification (No Initial Refusal, Initial Refusal)
- Size of MEPS family (1,2,3,4,5+)
- Metropolitan statistical area (MSA, nonMSA)
- Age (<20, 20-29, 30-44, 45-64, 65+)
- Marital Status of Reference Person (Married, Widowed, Divorced, Separated, Never Married)
Overall, 218 cells were identified based on
cross-classifications of these measures with cell collapsing specified according
to a hierarchy determined by significance level. The nonresponse adjustment for
the c-th weighting class takes the form:
where WGTSP1(I) is the MEPS Round 1
poststratified person level weight for the ith Round 1 respondent,
and WGTSP1(I) = WGTRU(1) for key and inscope respondents who joined a household
in 1996 after Round 1 (here, the new respondent acquires the sampling weight of
the family joined):
E(I)=1 for all MEPS Round 1 respondents with positive
values of WGTSP1(I), and for key and inscope respondents who joined a
responding household in 1996 after Round 1 with positive values of
WGTSP1(I), E(I)=0 otherwise;
R(I)=1 for all persons with E(I) = 1 who responded for
their entire period of eligibility in 1996, R(I)=0 otherwise;
and I e c represents all key
and inscope MEPS full and part-year respondents classified in weighting
class c.
Consequently, the estimation weight adjusted for survey
attrition in MEPS covering calendar year 1996, WGTSP2(I), for the ith
person associated with class c, takes the form:
WGTSP2(I) = F(c) x WGTSP1(I).
for the 21,571 key and inscope survey participants that
responded for their entire period of eligibility in 1996.
Return To Table Of Contents
4.8 MEPS Full Year 1996 Person Level Estimation Weights
The subset of the 21,571 key and inscope survey participants
that responded for their entire period of eligibility in 1996, who were also
inscope on December 31, 1996, had their part-year nonresponse adjusted annual
estimation weights further poststratified to Census Bureau population estimates
as of December 1996. The person level estimation weights, WGTSP2(I), of the
21,326 sample participants that meet this criteria were poststratified to
population totals obtained from the March 1997 CPS and further scaled to reflect
Census Bureau population estimates as of December, 1996, within weighting
classes defined by a cross-classification of the following variables:
- Sex: Male, Female;
- Age as of 12/31/96: <1, 1-4, 5-9, 10-14, 15-19, 20-24, 25-29, 30-34,
35-44, 45-54, 55-59, 60-64, 65-69, 70-74, 75-79, 80+.
- Race/ethnicity: Hispanic, Black-nonHispanic, Other-nonHispanic;
- Region: Northeast, Midwest, South and West;
- Metropolitan statistical area (MSA, nonMSA)
Within each of the weighting classes (ce
C) associated with a given age by sex cross-classification, the population
totals derived from the March 1997 CPS were further adjusted by the factor,
SCALE(C), which was defined as the ratio of the December, 1996 Census Bureau
population estimate to the March 1997 population estimate derived from the CPS
(see Table 2 on next page).
More specifically, the person level poststratification
adjustment for the c-th weighting class takes the form:
where MAR97CPS(c) represents the national
population estimate at the person level for weighting class c, derived from the
March 1997 Current Population Survey; SCALE(c) represents the ratio of
the December, 1996 Census Bureau population estimate to the March 1997
population estimate derived from the CPS for the specific cross-classification
of age and sex associated with cell C; ie c
represents all key and inscope survey participants associated with cell c (ce
C) that responded for their entire period of eligibility in 1996, and were also
inscope on December 31, 1996; and WGTSP2(I) represents the annual person
level estimation weight adjusted for survey attrition in MEPS covering calendar
year 1996. Consequently, the MEPS full year 1996 person level weight WGTSP96(I),
for the ith key, full year survey participant in scope as of 12/31/96
who is associated with class c, adjusted to population estimates derived from
the March 1997 Current Population Survey and further scaled to Census Bureau
estimates for December 1996, takes the form:
WGTSP96(I) = G(c) x WGTSP2(I).
The remaining 245 key, inscope MEPS survey participants who
responded for their entire period of eligibility in 1996, but were not inscope
as of December 31, 1996 (e.g., persons who died during the survey year),
maintained their estimation weight adjusted for survey attrition. Consequently,
their MEPS full year person level weight was specified as
WGTSP96(I) = WGTSP2(I).
The weighted estimate of the number of persons who are
members of the U.S. civilian non-institutionalized population as of December
1996 is 265,439,511. It can be derived by summing the poststratified MEPS person
weights for the 21,326 MEPS key and inscope survey participants classified as
respondents and inscope as of December 31, 1996, as indicated on the MEPS
Household Component Public Use File HC-003:1996 Panel, Full Year Utilization
Estimates.
Analysts who desire to produce cross-sectional national
insurance coverage estimates as of December, 1996 with the MEPS data are advised
to restrict their sample to this set of survey participants who were in scope as
of 12/31/96.
Similarly, the weighted estimate of the number of persons who are members of
the U.S. civilian non-institutionalized population over the course of 1996 is
268,130,477. It can be derived by summing the final poststratified MEPS person
weights for the 21,571 MEPS key and inscope survey participants who responded
for their entire period of eligibility in 1996. Analysts who desire to produce
annual 1996 health care utilization and expenditure estimates are advised to
include all of these 21,571 key and inscope MEPS survey participants for
the purposes of estimation. A future MEPS data release will include estimation
weights to support annual 1996 family-level health care use and expenditure
estimation.
|
Table
2. Population estimates by sex and age for December 1996 and March 1997
|
|
|
December 19961/ |
|
March 19972/ |
|
Age
Categories |
Male |
Female |
|
Male |
Female |
|
0 |
1,989,676 |
1,902,075 |
|
1,959,414 |
1,856,886 |
|
1-4 |
8,162,745 |
7,787,372 |
|
8,118,381 |
7,846,632 |
|
5-9 |
10,322,287 |
9,848,773 |
|
10,428,712 |
9,842,699 |
|
10-14 |
9,990,073 |
9,526,892 |
|
9,970,793 |
9,534,281 |
|
15-19 |
9,723,221 |
9,327,806 |
|
9,766,326 |
9,377,121 |
|
20-24 |
8,728,774 |
8,730,416 |
|
8,635,045 |
8,719,707 |
|
25-29 |
9,354,544 |
9,674,812 |
|
9,450,287 |
9,636,289 |
|
30-34 |
10,339,061 |
10,652,556 |
|
10,242,979 |
10,548,081 |
|
35-44 |
21,458,434 |
22,046,082 |
|
21,546,881 |
22,147,277 |
|
45-54 |
16,001,003 |
16,759,899 |
|
16,063,859 |
16,891,429 |
|
55-59 |
5,446,069 |
5,892,934 |
|
5,569,213 |
6,003,373 |
|
60-64 |
4,644,237 |
5,191,637 |
|
4,686,964 |
5,206,925 |
|
65-69 |
4,415,868 |
5,236,207 |
|
4,321,136 |
5,179,642 |
|
70-74 |
3,721,987 |
4,787,277 |
|
3,764,159 |
4,750,254 |
|
75 or older |
5,280,322 |
8,496,472 |
|
5,318,511 |
8,543,637 |
|
Total |
129,578,301 |
135,861,210 |
|
129,842,460 |
136,084,232 |
Notes: 1/ December 1996 estimates are obtained from the Bureau
of the Census.
2/ March 1997 estimates are computed from the CPS, March 1997 data
file. Return To Table Of Contents
5.0 Variance Estimation
The sample design of the MEPS Household Component includes
stratification, clustering, multiple stages of selection, and disproportionate
sampling. This complex sample design results in serious departures from simple
random sampling assumptions. Furthermore, the MEPS sampling weights reflect
differential adjustments for survey nonresponse and poststratification. These
survey design and estimation complexities requires special consideration with
regard to variance estimation and analysis. To obtain accurate estimates of the
standard errors associated with MEPS person and family level survey estimates,
for either descriptive statistics or more sophisticated multivariate model-based
analyses, the MEPS survey design complexities need to be taken into account.
Several methods for estimating sampling variances which adjust for survey design
complexities have been developed that are appropriate for analytical
applications tied to MEPS (Cohen, 1997). These variance estimation strategies
include the Taylor series linearization method, balanced repeated replication
and the jack-knife method.
Variables necessary for implementing a Taylor series variance
estimation approach for survey estimates have been included on the MEPS public
use files. Using such an approach, the sampling strata and associated primary
sampling units (PSU) that define the MEPS survey design need to be specified.
The corresponding variables on the MEPS Round 1 data base are VARSTRT1 and
VARPSU1, respectively. Similarly, the corresponding variables on the MEPS Full
Year 1996 Utilization Estimates data base are VARSTR96 and VARPSU96. Specifying
a "with replacement" design in a variance estimation software package
appropriate for the analysis of complex survey data that utilizes the Taylor
series approach, such as SUDAAN or Stata, will yield standard errors that have
been appropriately adjusted for survey design complexities (Shah et al., 1996).
It should be noted that the number of degrees of freedom
associated with estimates of variability obtained by application of these
statistical software packages may not appropriately reflect the actual number.
For MEPS sample estimates for the general population derived at the national
level, it is estimated that there are approximately 170 degrees of freedom for
purposes of variance estimation. Return To Table Of Contents
6.0 Summary
As a consequence of the national scope and depth of the MEPS
data collection effort, and the use of resultant survey estimates to inform
national health policies, the adoption of estimation strategies that improve the
quality and accuracy of survey estimates is of particular importance. Research
was conducted to help ascertain potential sources of nonresponse bias that were
attributable to MEPS dwelling unit nonresponse and to incorporate the findings
in the specification of the MEPS nonresponse adjustment strategy to help reduce
the impact of nonresponse bias. As a consequence of the MEPS sample linkage to
the NHIS, detailed information on the socio-demographic and health
characteristics of the eligible MEPS sample was available to inform the
investigation. The results of this investigation revealed that the dwelling
units responding to the first round of the MEPS household survey differed from
the nonrespondents on a number of dimensions. Based on the results of the
multivariate analysis, the effects of family income, dwelling unit size, health
status of household members (as measured by personal help needs), phone
availability, MSA size, and item nonresponse for employment classification, were
significant factors in distinguishing MEPS respondents. The measures most
significant in differentiating MEPS survey response status were used in the
specification of the MEPS Round 1 dwelling unit nonresponse adjustments. Through
the identification of weighting classes in MEPS that capture the greatest
variation across subgroups in response rates, a reduction in the bias
attributable to survey nonresponse should be achieved.
An analysis of the characteristics that distinguish MEPS
respondents with survey response for their entire period of eligibility in 1996,
relative to the Round 1 participants that discontinued survey participation, was
also conducted to identify the most important measures to include in the
specification of a nonresponse adjustment to the MEPS estimation weights to
correct for part-year survey nonresponse. The results of a logistic regression
analysis that identified characteristics that distinguished the MEPS full year
respondents from their part-year respondent counterparts identified the most
important measures to include in the specification of a nonresponse adjustment
to the MEPS sampling weights to correct for part-year response for calendar 1996
at the person level. Family size, residence by MSA classification, age, marital
status and reluctance to participate were found to be important factors in
distinguishing the MEPS full year respondents from their part year counterparts.
The overall MEPS person level response rate for deriving
annual 1996 estimates was 70.2 percent, after adjusting for the multiplicative
effects of nonresponse to the NHIS, nonresponse to the first round of the MEPS
and the impact of survey attrition. Additional poststratification adjustments
were incorporated in the development of the annual MEPS estimation weights, to
further improve the accuracy of resultant MEPS survey estimates. The
poststratification adjustments relied on population estimates derived from the
Current Population Survey and other Census Bureau sources. A detailed summary of
the MEPS estimation weight specifications has been provided in this report to
ensure a better understanding of the estimation procedures that were adopted. Return To Table Of Contents
7.0 References
Arnett, R.A., E. Hunter, S. Cohen, J. Madans, and J. Feldman
(1996). The Department of Health and Human Services’ Survey Integration Plan. American
Statistical Association, Proceedings of the Section on Government Statistics.
Berk, M.L. and A.B. Bernstein (1984). Interviewer
Characteristics and Performance on a Complex Health Survey. American
Statistical Association, Proceedings of the Section on Survey Research Methods.
Cohen, S.B. and S.R. Machlin (1998). "Characteristics of
Nonrespondents in the MEPS Household Component". Submitted for publication
consideration in The Journal of Economic and Social Measurement.
Cohen, S. B. (1997). "An Evaluation of Alternative
PC-Based Software Packages Developed for the Analysis of Complex Survey
Data". The American Statistician. Vol. 51, No. 3. 285-292.
Cohen, S. B. (1997). "Sample Design of the 1996 Medical
Expenditure Panel Survey Household Component". Rockville (MD): Agency for
Health Care Policy and Research; 1997. MEPS Methodology Report, No. 2.
AHCPR Pub. No. 97-0027.
Cohen, J. W. (1997). "Design and Methods of the Medical
Expenditure Panel Survey Household Component". Rockville (MD): Agency for
Health Care Policy and Research; 1997. MEPS Methodology Report, No. 1.
AHCPR Pub. No. 97-0026.
Cohen, S. B. (1996). The Redesign of the Medical Expenditure
Panel Survey: A Component of the DHHS Survey Integration Plan. Proceedings of
the COPAFS Seminar on Statistical Methodology in the Public Service..
Cohen, S.B. and B.L. Carlson (1995). Characteristics of
Reluctant Respondents in the national Medical Expenditure Survey. Journal of
Economic and Social Measurement. 21: 269-296.
Cox, B.G. and S.B. Cohen (1985). Methodological Issues for
Health Care Surveys. Marcel Dekker, New York.
DiGaetano, R. And H. Goksel (1996). Internal Report on
Factors Associated With MEPS Round 1 Dwelling Unit Nonresponse. Westat, Inc.
Judkins, D., D. Marker and J. Waksberg (1994). National
Health Interview Survey: Research for the 1995 Redesign, Draft Report. Westat
Report prepared for the National Center for Health Statistics.
Shah, B.V., B. G. Barnwell, G.S. Bieler, K.E. Boyle, R.E.
Folsom, L. Lavange, S.C. Wheeless, and R. Williams (1996). Technical Manual:
Statistical Methods and Algorithms Used in SUDAAN Release 7.0, Research
Triangle Park, NC: Research Triangle Institute.
Singer, E. M. Frankel and M. Glassman (1983). The Effect of
Interviewer Characteristics and Expectations on Response. Public Opinion
Quarterly. 47:68-83. Return To Table Of Contents
Appendix 2: Sample Design of the 1997 Medical Expenditure Panel Survey: Household Component
Steven B. Cohen, Ph.D.
Division of Statistical Research and Methods
Center for Cost and Financing Studies
Agency for Healthcare Research and Quality
1.0 Introduction
The Household Component of the 1997 Medical Expenditure Panel
Survey (MEPS) was designed to produce national and regional estimates of the
health care use, expenditures, sources of payment, and insurance coverage of the
U.S. civilian noninstitutionalized population. MEPS includes surveys of medical
providers, employers, and other health insurance providers to supplement the
data provided by household respondents. The MEPS design permits both
person-based and family-level estimates. Government agencies, legislative
bodies, and health professionals need comprehensive national estimates to use in
formulating and analyzing national health policies. The scope and depth of this
data collection effort reflect this need. MEPS collects data on the specific
health services that Americans use, how frequently they use them, the cost of
these services, and how they are paid for, as well as data on the cost, scope,
and breadth of private health insurance held by and available to the U.S.
population. MEPS is unparalleled for the degree of detail in its data. In
addition, through MEPS, the medical expenditures and health insurance data of
survey respondents can be linked to other characteristics such as demographic
variables, employment status, economic status, health status, and use of health
services. Moreover, MEPS is the only national survey that provides a foundation
for estimating the impact of changes in sources of payment for health services
and insurance coverage on different economic groups or special populations of
interest, such as the poor, the elderly, veterans, the uninsured, and racial and
ethnic minorities.
The MEPS reflects the first stage of implementation of the
Department of Health and Human Services (DHHS) Survey Integration Plan, which
provides directives targeted to improve the analytic capacity of programs, fill
major data gaps, and establish a framework in which DHHS data activities are
streamlined and rationalized. Through this effort, specifically through a
linkage to NHIS, MEPS has achieved a number of significant design improvements
and analytic enhancements (S. Cohen, 1997, J. Cohen, 1997, Arnett et al., 1996,
Hunter et al., 1997). Return To Table Of Contents
In this report, the sample design of the Household Component
of the 1997 MEPS is described in detail. Particular emphasis is given to a
description of the overlapping panel design that characterizes the survey.
Attention is given to the sample selection scheme implemented to facilitate an
oversample of the functionally impaired, children with activity limitations,
individuals predicted to incur high medical expenditures and individuals
predicted to have incomes less than 200% of poverty level. The report also
includes a summary of sample size specifications, survey response rates and
targeted precision levels for national population estimates and health care
expenditure estimates for policy-relevant population subgroups. Return To Table Of Contents
2.0 Sample Design
To fill major data gaps identified by the Department of
Health and Human Services, the Medical Expenditure Panel Survey was specified as
a continuous survey. The sample design of the 1997 MEPS Household Component is
an overlapping panel design. Health care data are collected for each new MEPS
sample (Panel) to cover a two-year period, with the first two MEPS Panels
spanning 1996-97 and 1997-98, respectively. To produce health care estimates for
calendar year 1997, the data are pooled across the two distinct nationally
representative MEPS samples. More specifically, the 1997 design combines the
second year of the first MEPS panel and the first year of the second MEPS panel.
The National Health Interview Survey (NHIS) serves as the sampling frame for the
MEPS. The NHIS is an ongoing annual household survey of approximately 42,000
households (109,000 individuals) conducted by the National Center for Health
Statistics (NCHS) to obtain national estimates on health care use, health
conditions, health status, insurance coverage, and access for the U.S. civilian
noninstitutionalized population. In addition to the cost savings achieved by
substituting the NHIS as the MEPS sample frame, relative to the use of an
independent national screener sample, this design feature enhances the analytic
capacity of the resultant survey data. Use of the NHIS data in concert with the
MEPS data provides an additional capacity for longitudinal analyses not
available in the prior national medical expenditure surveys sponsored by the
Agency for Healthcare Research and Quality (AHRQ) (S.Cohen, 1996).
The analytical goals of the 1997 Medical Expenditure Panel
Survey and budget constraints required that the sample design for the Household
Component meet the following requirements:
- The full series of interviews for the pooled MEPS samples covering
calendar year 1997 should be completed in approximately 13,500 households.
- The sample should be spread over 195 separate areas to represent the
civilian noninstitutionalized population of the 50 States and the District
of Columbia.
- The sample should yield approximately unbiased national estimates of the
health care parameters under study and estimates of adequate precision for
the four census regions.
- The sample should meet predesignated precision specifications for the
following population subgroups of analytical interest: blacks, Hispanics,
the functionally impaired, children with activity limitations, individuals
predicted to have high medical expenditures, and persons predicted to have
family income less than 200 percent of the poverty level.
The 1996 MEPS Household Component sample was selected from
households that responded to the 1995 NHIS. NHIS is designed to permit the
selection of nationally representative subsamples from any one of four panels.
Furthermore, any combination of one to four panels will provide a nationally
representative sample of households. Each NHIS panel subsample for a given
quarter of a calendar year is nationally representative. The 1996 MEPS household
sample was selected from two of the four 1995 NHIS panels during the second and
third quarters of 1995. Consequently, the MEPS sample is an approximately 1/4
sub-sample of the overall 1995 NHIS sample. Return To Table Of Contents
The complete 1995 NHIS sample (panels 1-4) consists of 358
primary sampling units, or PSUs (which are counties or groups of contiguous
counties), and approximately 42,000 responding households. The NHIS sample
design is characterized by a stratified multi-stage area probability design,
where the sample PSUs are stratified by geographic area (Census region and
State), metropolitan status, and sociodemographic measures (Judkins, Marker, and
Waksberg, 1994). Within sample PSUs, a sample of blocks (segments) was selected
after the blocks were stratified by measures of minority population density that
allowed for an oversample of areas with high population concentrations of blacks
and Hispanics. A nationally representative sample of approximately 71,000
addresses within sampled blocks was selected and targeted for further screening
to facilitate an oversample of blacks and Hispanics as part of the 1995 NHIS
interview.
The 1995 NHIS subsample selected for the 1996 MEPS consists
of 195 PSUs. In the two targeted quarters of 1995, these PSUs included 1,675
sample segments (second-stage sampling units) and 10,597 responding households.
This NHIS sample reflects oversampling of households with Hispanics and blacks
at a ratio of approximately 2.0:1 for Hispanics and 1.5:1 for blacks. This 1996
MEPS sample constitutes a panel that was surveyed to collect annual data for 2
consecutive years (S. Cohen, 1997).
A new 1997 MEPS panel sample was selected as a nationally
representative subsample of households responding to the 1996 NHIS. More
specifically, this 1997 MEPS sample was selected from the same two NHIS panels
used for the 1996 MEPS, using a nationally representative subsample of the 1996
NHIS that also reflected an oversample of Hispanics and blacks at the same
ratios as the 1995 NHIS (Hispanics, 2.0:1; blacks, 1.5:1). It should be noted
that in 1996, the National Health Interview Survey was undergoing a transition
from a paper and pencil survey administration design to a computer assisted
personal interview. The nationally representative subsample of the NHIS reserved
for the 1997 MEPS sample selection retained the paper and pencil survey
administration mode, to allow for a smoother transition between the integration
of the two national surveys.
The new 1997 MEPS sample was selected from the first three
quarters of the 1996 NHIS subsample within the two panels reserved for the MEPS.
This NHIS nationally representative subsample was concentrated within the same
195 PSUs selected for the 1996 MEPS household sample and consisted of 14,706
responding NHIS dwelling units. A nationally representative subsample of 6,300
NHIS responding dwelling units (consisting of 6,480 reporting units) was
selected to serve as the new 1997 MEPS sample. In addition to retaining the
oversample of minorities that characterized the NHIS sample design, the 1997
MEPS was designed to oversample the following policy-relevant subgroups:
functionally impaired adults, children limited in activities, adults predicted
to have high medical expenditures, and persons predicted to have family incomes
less than 200 percent of the poverty level. The new 1997 MEPS panel was designed
to collect annual data for 2 consecutive years. Consequently, the full 1997 MEPS
Household Component sample consists of the first year of the 1997 MEPS panel
pooled with the second year of the 1996 MEPS sample. Return To Table Of Contents
Sampling Unit Definitions and Eligibility Criteria
The definitions for dwelling units and group quarters in the
MEPS Household Component are generally consistent with the definitions employed
for NHIS. More specifically, a dwelling unit is a house, apartment, group of
rooms, or single room occupied as separate civilian non-institutional living
quarters or vacant but intended for occupancy as separate living quarters. Group
quarters consist of a single civilian noninstitutional dwelling or structure in
which nine or more unrelated persons reside and where inhabitants are not
considered a part of any other dwelling unit. A reporting unit is a person or
group of persons in the sampled dwelling unit that are related by blood,
marriage, adoption, or other family associations, and are to be interviewed at
the same time in MEPS. Examples of discrete reporting units follow.
- A married daughter and her husband living with her parents in the same
dwelling are considered one reporting unit.
- A husband and wife and their unmarried daughter, age 18, who is living
away from home at college constitute one family, but two reporting units.
- Three unrelated persons living in the same dwelling unit would be three
reporting units.
College students under 24 years of age who usually live in
the sampled household but are currently living away from home and going to
school are treated as separate reporting units for the purpose of data
collection.
The new 1997 MEPS sample consisted of households (dwelling
units) that responded to the 1996 NHIS in the two panels reserved for MEPS, with
the basic unit of analysis defined as the person, which mirrored the 1996 MEPS
design. Analysis is planned using both the individual and the family as units.
Through the reenumeration section of the Round 1 questionnaire for each MEPS
panel, the status of each individual sampled at the time of the NHIS interview
is classified as "key" or "non-key," "inscope" or
"out-of-scope," and "eligible" or "ineligible" for
MEPS data collection. For an individual to be inscope and eligible for
person-level estimates derived from the MEPS household survey, he or she must be
a member of the civilian noninstitutionalized population for some period of time
in the calendar year of analytic interest. Because a person’s eligibility for
the survey may change after the NHIS interview, sampling reenumeration takes
place in each subsequent reinterview for persons in all households selected into
the core survey. The keyness, inscope, and eligibility indicators, together,
define the target sample to be used for person-level national estimates. Only
persons who are key, inscope, and eligible for data collection are considered in
the derivation of person-level national estimates from MEPS. Return To Table Of Contents
Key Persons
Key survey participants are defined as all civilian
noninstitutionalized individuals who resided in households that responded to the
nationally representative NHIS subsample reserved for MEPS (e.g., 6,300
households from the 1996 NHIS), with the exception of college students
interviewed at dormitories. Members of the Armed Forces who are on full-time
active duty are also defined as key persons if they reside in responding NHIS
households that include other family members who are civilian
noninstitutionalized individuals. However, they are out of scope for
person-level estimates derived from the survey.
All individuals who join the NHIS reporting units that define
the 1997 MEPS household sample (in Round 1 or later MEPS rounds) and were not
available for selection during the time of the NHIS interview are also
considered key persons. These include newborn babies, individuals who were in an
institution or outside the country, and military personnel previously residing
on military bases.
College students under 24 years of age interviewed at
dormitories in the 1996 NHIS are not included in the 1997 MEPS sample, since
this population subgroup will be targeted through their parents during the MEPS
interview. The same rule applied for the sample selected for the 1996 MEPS
sample selected from the 1995 NHIS. Furthermore, any unmarried college student
under 24 years of age who responded to the 1996 NHIS interview while living away
at school (not in a dormitory) is excluded from the sample if it is determined
in the MEPS Round 1 interview that the person is unmarried, under 24 years of
age, and a student who has parents living elsewhere and who resides at his or
her current housing only during the school year. If, on the other hand, the
person's status at the time of the MEPS Round 1 interview is no longer that of
an unmarried student under 24 years of age living away from home, then the
person is retained as a key person.
Additionally, during the MEPS Round 1 interview with NHIS
sample respondents, a determination is made whether there are any related
college students under 24 years of age who usually live in the sampled household
but are currently living away from home and going to school. These college
students are considered key persons and are identified and interviewed at their
college address but linked to the sampled household for family analyses. Some of
these college students will have been identified as living in the sampled
household at the time of the 1995 NHIS interview. The remainder are identified
at the time of the MEPS Round 1 interview. Return To Table Of Contents
Non-Key
Persons
Persons who were not living in the original sampled dwelling
unit at the time of the 1996 NHIS for the 1997 new MEPS sample interview (the
1995 NHIS for the original 1996 MEPS sample) and who had a nonzero probability
of selection for that survey are considered non-key. If such persons happen to
be living in sampled households in Round 1 or later rounds, MEPS data are
collected for the period of time they are part of the sampled unit to permit
family analyses. Non-key persons who leave any sampled household are not
re-contacted for subsequent interviews. Non-key individuals are not part of the
target sample used to obtain person-level national estimates.
A key person from the NHIS sampled household selected for
MEPS may move out in Round 1 or later rounds and join or create another family.
Data on all members of this new household who are related by blood, marriage,
adoption, or foster care to the person from the NHIS sampled household are
obtained from the time that the sampled person joined the household. Keyness
status is determined for these new members based on their probability of
selection for the NHIS. If it is positive, they are classified as non-key.
Similarly, data are collected in Round 1 and later rounds on all related persons
who join NHIS sampled households selected into MEPS.
Persons in NHIS sampled households selected in MEPS may
subsequently enter an institution, thus no longer qualifying as a member of the
U.S. civilian noninstitutionalized population. For those who enter nursing
homes, data collection continues during the nursing home stay. For those who
enter other institutions, data collection is suspended while they are
institutionalized, but their whereabouts are monitored during the field period.
If they rejoin the U.S. civilian noninstitutionalized population, HC data
collection resumes. (This is also the procedure for those entering military
service away from home or moving out of the United States.)
MEPS
Data Collection Eligibility
In order for a MEPS reporting unit to be eligible for data
collection, it must include at least one individual who is key and inscope for
some period of time during the reference period for a given round of data
collection. If this condition holds, the persons who are key and inscope and all
other individuals who are members of the reporting unit (living together and
related by blood, marriage, adoption, or other family associations) are eligible
for data collection in a given round of MEPS. Return To Table Of Contents
3.0 Sample Selection of the 1997 MEPS Panel
Sample
Size Targets and Precision Requirements
An overall precision requirement for the 1997 MEPS survey was
the achievement of an average design effect of 1.7 for the survey estimates of
the policy relevant population subgroups. The precision requirements for the
1997 HC are presented in Table 1. They are presented in terms of relative
standard errors for the following survey estimates:
1) a 20 percent population estimate at the person level
for each specified domain (e.g. a percent population estimate such as the
rate of the uninsured for the population under age 65); and
2) mean estimates of the following measures of health
care utilization and expenditures at the person level (precision requirement
specified as an average relative standard error):
a. total health expenditures;
b. utilization and expenditure estimates for
inpatient hospital stays;
c. utilization and expenditure estimates for
ambulatory physician visits;
d. utilization and expenditure estimates for dental
visits;
e. utilization and expenditure estimates for
prescribed medicines.
Table 1:Targeted average relative standard errors (RSE’s)
for subpopulations of analytic interest in the 1997 MEPS
|
Subpopulation |
Average RSE for a population estimate of 20% (e.g.
% uninsured) |
Average RSE for mean use and expenditure estimates |
|
Persons with family incomes less than 200% of poverty level |
.020 |
.035 |
|
Persons predicted to incur high medical expenditures |
.040 |
.070 |
|
Persons 65 years or older |
.042 |
.070 |
|
Adults (18+) with functional impairments (1 or more activities of daily living (ADLs)) |
.080 |
.135 |
|
Adults (18+) with other impairments (1 or more instrumental activities of daily living (IADLs)), |
.080 |
.135 |
|
Children with limitations (age 17 or younger) |
.080 |
.135 |
|
Overall population |
.015 |
.023 |
Source: 1997 Medical Expenditure Panel Survey, AHRQ
Return To Table Of Contents
The 1997 MEPS person level precision requirements are
specified for estimates derived from individuals that are considered full year
respondents (individuals with responses for their entire period of eligibility
in 1997). Consequently, in the determination of sample sizes necessary to
achieve the precision requirements, additional adjustments must be made for
survey nonresponse to obtain the targeted number of full year respondents.
Approximately 34,000 persons completing the three core MEPS household interviews
to cover calendar year 1997 (Rounds 1-3 for the new 1997 MEPS sample; Rounds 3-5
for the carry-over 1996 MEPS sample) were targeted for sample selection to
achieve the desired precision specifications for national population estimates.
Assuming 2.5 persons per original sampled reporting unit, approximately 13,600
families completing the three rounds in 1997 were estimated as the necessary
sample yield to meet precision specifications. Table 2 indicates the desired
number of persons in the various subpopulations of interest for analysis
necessary to satisfy the survey precision requirements for the pooled 1996 and
1997 MEPS samples to permit 1997 population estimates.
Table 2. Targeted sample yields at the end of three core data
collection rounds for 1997 for subpopulations of analytic interest.
|
Subpopulation |
Targeted sample yield |
|
Persons under 200% of poverty level |
15,000 |
|
Persons under age 65 with predicted high medical expenditures (top 15 % of the expenditure distribution) |
4,000 |
|
Persons 65 years or older |
3,700 |
|
Adults (18+) with functional impairments (1 or more ADLs) |
1,000 |
|
Adults (18+) with other impairments (1 or more IADLs) |
1,000 |
|
Children with limitations (age 17 or younger) |
1,000 |
|
Overall population |
34,000 |
Source: 1997 Medical Expenditure Panel Survey, AHRQ Return To Table Of Contents
Precision requirements for the 1997 MEPS Household Survey
were stated in terms of national estimates at the person level. To meet these
requirements, the survey must include a minimum number of persons in each domain
of interest. The prior 1996 MEPS sample was also selected to satisfy distinct
precision requirements at the person level for overall population estimates and
for subgroup analyses of blacks and Hispanics for calendar year 1996 (S. Cohen,
1997). Projected yields in 1997 from the first MEPS Panel were derived to inform
the specification of the final selection rates for the new 1997 MEPS sample in
order to satisfy precision requirements for the pooled 1997 MEPS sample. Based
on these projected sample yields (actual sample yields presented in Table 4),
the additional sample sizes necessary to satisfy the precision requirements for
the analytical domains were determined, after adjusting for expected survey
response rates, and sampling rates were specified for the new 1997 sample to
achieve these targets.
For both the 1996 and the 1997 MEPS, the unit of interviewing
and subsampling was the household. To facilitate the sample selection of the new
1997 MEPS sample, the 1996 NHIS households were selected on the basis of the
characteristics of the persons they included. There were seven sample domains of
interest to which a NHIS dwelling unit could be assigned based on its
composition with at least one member having the characteristic of interest:
-
adults (age 18 and above) with functional impairments (at least 1 ADL
requiring personal assistance);
-
children with limitations in activity (under age 18);
-
individuals 18-64 years old with predicted high medical expenditures
(predicted probability is greater than or equal to .4, using the MEPS
prediction model to identify likely high expenditure individuals);
-
individuals with family incomes likely to be below 200% of poverty level
(predicted probability is greater than or equal to .3, using the MEPS
prediction model to identify low income households);
-
Adults with other impairments (ages18-69 and at least 1 IADL and unable to
work , age 70 and above and at least 1 IADL);
-
elderly individuals (age 65 and above); and
-
all remaining individuals.
These sampling domains were not mutually exclusive, but their
order reflects the hierarchy of their sampling priority. For purposes of
sampling, dwelling units containing members having the above characteristics
were hierarchically classified based on the above ordering to form seven
mutually exclusive and exhaustive sampling strata (DiGaetano, 1994). Return To Table Of Contents
Using Predictive Models for Domain Assignments
Poverty Status Model
Since a reporting unit’s poverty status classification in
1997 was unknown at the time of the administration of the 1996 NHIS interview, a
prediction model was used to determine whether a household was to be
oversampled. More specifically, a logistic regression model was developed to
estimate the probability that a reporting unit would have a family income less
than 1.25 times the poverty level in a subsequent year based on the poverty
status classification and other predictive measures obtained during the NHIS
interview. Households with predicted probabilities above a certain threshold
value were to be oversampled. In addition to facilitating an oversample of
individuals with family incomes less than 125 percent of the poverty level, use
of this prediction model was expected to facilitate an oversample of individuals
with family incomes less than 200 percent of the poverty level. Consequently,
all reporting units with a predicted probability of .3 or greater were
classified as households predicted to have family incomes less than 200 percent
of the poverty level.
The results listed below were observed based on an evaluation
of the model’s performance at the reporting unit level, using data from the
prior 1987 National Medical Expenditure Survey (NMES2), and using a predicted
probability of .3 or greater (derived from the logistic regression prediction
model) as the criterion to target reporting units most likely to have members
with family income less than 200 percent of the poverty level in 1996:
-
Based on the NMES2 experience, the expected prediction rate for true
positives (family income less than 200 percent of the poverty level) is 83.1
percent among the 19.5 percent of reporting units predicted to have members
with family income less than 200 percent of the poverty level.
-
The expected prediction rate for false negatives is 17.1 percent among the
80.5 percent of reporting units predicted to have family income equal to or
greater than 200% of the poverty level.
Among the 30 percent of reporting units with family income
less than 200 percent of the poverty level, 54 percent were predicted to have
members with family income less than 200 percent of the poverty level.
Alternatively, among the 70 percent of reporting units with family income above
200 percent of the poverty level, 95.3 percent were predicted to have members
with family income above 200 percent of the poverty level.
The logistic regression model that was adopted was specified
at the reporting unit level and required data on the following measures obtained
in the NHIS interview (Moeller and Mathiowetz, 1994):
-
Age of reference person;
-
Home ownership;
-
Reporting Unit size;
-
Whether children of specific ages (under age 6, 6-15) are present in the
RU;
-
Whether someone in the RU other than the reference person is at least
65 years of age;
-
Health status of reference person;
-
Race/ethnicity of reference person;
-
Census Division;
-
Metropolitan Statistical Area (MSA) status of PSU;
-
Education of reference person;
-
Marital status and gender of reference person;
-
Whether reference person or spouse was employed in the previous
3 months;
-
Whether the family income of the reporting unit was less than 1.25 times
the poverty level; and
-
Whether anyone in the RU was covered by Medicaid.
Return To Table Of Contents
High Expenditure Prediction Model
Among the sample domains to be oversampled in the main survey
are individuals between the ages 18-64 who are predicted as likely to incur high
medical expenditures. An individual’s medical care expenditures in a future
year will be unknown at the time of the administration of the 1996 NHIS
interview; therefore, a prediction model based on NMES2 data was used to
determine whether a household is to be oversampled as part of the high medical
expenditures group because one or more of the family members are expected to
incur high medical expenditures in the subsequent year. More specifically, a
logistic regression model has been developed that estimates the expected
probability an individual who is between the ages of 18-64 will incur high
medical expenditures (top 15 percent of the health expenditure distribution) in
a subsequent year based on predictive measures obtained during the NHIS
interview. Households with at least one such person with a predicted probability
above a certain threshold value were oversampled. The group was restricted to
individuals who were between the ages 18-64, since the persons 65 or older that
were functionally impaired were separately targeted to be oversampled. For
purposes of sampling, all individuals with a predicted probability of .4 or
greater were classified as likely to incur high medical expenditures in the
subsequent year. This threshold was selected as the value that was expected to
best limit prediction errors.
The logistic regression model under consideration was
specified at the person level and requires data on the following measures
obtained in the NHIS interview (Moeller and Mathiowetz, 1994):
-
Gender
-
Health status;
-
Marital status;
-
Poverty status;
-
Whether the person lives alone;
-
Age;
-
Whether the person’s health keeps him/her from working at a job, doing
work around the house or going to school;
-
Whether the person is unable to do certain kinds or amounts of work,
housework, or schoolwork because of his/her health;
-
The number of visits to a medical doctor or other medical care provider
the person has had during the last 6 months;
-
The number of times prescribed medicines were purchased or obtained for
the person’s use in the last 6 months (an imputation strategy was used to
derive this measure since data were unavailable from the 1996 NHIS);
-
Census Division; and
-
MSA status of PSU.
Return To Table Of Contents
The results listed below were observed based on an evaluation
of the model’s performance at the individual level, using data from NMES2, and
using a predicted probability of .4 or greater (derived from the logistic
regression prediction model) as the criterion to target individuals who are
between the ages 18-64 and considered likely to incur high medical expenditures
in the subsequent year:
-
Based on the NMES2 experience, the expected prediction rate for true
positives is 37.7 percent among the 14.1 percent of individuals in reporting
units (computed at the reporting unit level) with members between the ages
18-64 who are predicted to incur high medical expenditures in the subsequent
year. It should be noted that when restricting the evaluation to the subset
of individuals (8.1 percent) that are predicted to incur high medical
expenditures, the expected prediction rate for true positives is 65.3
percent (computed at the person level).
-
The expected prediction rate for false negatives is 11.3 percent among the
85.9 percent of individuals in reporting units (computed at the reporting
unit level) with members between the ages 18-64 who are predicted to not
incur high medical expenditures in the subsequent year.
Sample Composition of 1996 NHIS Available for the 1997 MEPS
Sample
In order to provide the 1997 MEPS sample to Westat and NORC
(the MEPS data collection organizations) in the time frame specified to field
the survey in February of 1997, it was necessary to restrict the sample
selection from a nationally representative NHIS subsample confined to the first
three quarters of 1996. This NHIS sample of 14,706 responding dwelling units was
then classified into seven mutually exclusive and exhaustive sampling categories
based on the demographic characteristic of its "highest priority"
individual. This was the household member requiring the highest sampling rate to
meet sample size targets. The sampling classes presented in Table 3A are
arranged in order of highest priority. The table provides a distribution of the
14,706 responding NHIS dwelling units according to their sampling classes, the
MEPS sampling rates and the resultant sample of dwelling units selected for the
1997 MEPS. It should be noted that a dwelling unit with a higher order sampling
classification may include members with a characteristic of interest that
defines a lower sampling classification. More specifically, a dwelling unit with
a sampling classification of 1, which indicates the dwelling unit includes an
adult (age 18 and above) with functional impairments (at least 1 ADL requiring
personal assistance), may also include a member
with any of the other characteristics targeted for
oversampling: children with limitations in activity (under age 17); individuals
18-64 years old with predicted high medical expenditures; individuals with
family incomes likely to be below 200% of poverty level; adults with other
impairments (ages 18-69 and at least 1 IADL and unable to work , age 70 and
above and at least 1 IADL). However, dwelling units assigned to sampling classes
with lower priority do not include members with a characteristic that defines a
higher order classification. Return To Table Of Contents
For sampling purposes, a person was classified as having at
least 1 ADL requiring personal assistance if there was an affirmative answer to
the following question in the 1996 NHIS, "Because of any impairment
or health problem, does___need the help of other persons with personal care
needs, such as eating, bathing, dressing, or getting around this home?".
Similarly, a person was classified as having at least 1 IADL requiring
assistance if there was an affirmative answer to the following question in the
1996 NHIS, "Because of any impairment or health problem, does___ need
the help of others in handling routine needs , such as everyday household
chores, doing necessary business, shopping or getting around for other
purposes?"
All NHIS dwelling units assigned to the first three sampling
classes ordered by sampling priority were selected with certainty for inclusion
for the 1997 MEPS sample. This rate of selection was specified to satisfy sample
size targets for the pooled 1997 sample for individuals with one of the
following characteristics: adults with functional impairments (at least 1 ADL
requiring personal assistance), children with limitations in activity (under age
17), or individuals 18-64 years old predicted to incur high levels of medical
expenditures. Dwelling units associated with the next highest priority sampling
classes were then selected at a sampling rate of 0.6 designed to meet sample
size requirements for the survey. This rate of selection was specified to
satisfy sample size targets for the pooled 1997 sample for individuals with one
of the following characteristics: individuals with family incomes predicted to
be below 200% of poverty level, or adults with other impairments (at least one
IADL). All remaining dwelling units associated with the remaining sampling
classes were selected with a rate of 0.3 , again to satisfy sample size targets
for the 1997 MEPS.
Prior to sample selection, dwelling units within each of the
sampling classes were hierarchically sorted by the following measures:
-
Quarter of 1996 based on calendar year
-
Week within respective calendar quarter of 1996
-
Census division
-
State
-
MSA classification
-
NHIS primary sampling unit
-
NHIS segment within primary sampling unit
-
Minority classification of dwelling unit (Hispanic; Black-Non-Hispanic;
Other).
A random systematic sample of dwelling units was then
selected from the respective sampling class, using the specified sample
selection rate (Table 3A). Table 3B provides a distribution of the 15,067
responding NHIS reporting units within the dwelling units according to these
sampling classes, in addition to the MEPS sampling rates and the resultant
sample of 6,480 reporting units selected for the 1997 MEPS. In addition, Table
3C provides a distribution of the 38,418 responding NHIS individuals within the
dwelling units assigned to the hierarchically defined sampling classes, in
addition to the subsample of 17,063 individuals selected for the new 1997 MEPS
sample. Since individuals may be classified in more than one category based on
the sampling domains under consideration, the sample yields for the new 1997
MEPS sample, allowing for multiple classifications is presented in Table 3D
(Note that the sample distributions presented in Tables 3 A-D are confined to
the new panel of MEPS introduced in 1997). Return To Table Of Contents
|
Table 3A: NHIS dwelling unit sample classification
available for MEPS |
|
Available Sample |
1997 MEPS Subsample |
|
Dwelling Units with at least one member |
NHIS 1996 Frequency |
Frequency |
Sampling Rate |
|
1. Functionally impaired adults |
478 |
478 |
1.0 |
|
2. Children with activity limitations |
601 |
601 |
1.0 |
|
3. Individuals predicted to incur high expenditures |
596 |
596 |
1.0 |
|
4. Low income |
2,064 |
1,238 |
0.6 |
|
5.Adults with other limitations |
324 |
194 |
0.6 |
|
6. Adults aged 65 and older |
2,157 |
647 |
0.3 |
|
7. Other |
8,486 |
2,546 |
0.3 |
|
Total |
14,706 |
6,300 |
|
Source: 1996 National Health Interview Survey, National Center for Health
Statistics, CDC
Return To Table Of Contents
|
Table 3B: 1996 NHIS reporting unit sample
classification available for MEPS |
|
Available Sample |
1997 MEPS Subsample |
|
Reporting Units in dwelling units with at least one member |
1996 NHIS Frequency |
Frequency |
|
1. Functionally impaired adults |
481 |
481 |
|
2. Children with activity limitations |
601 |
601 |
|
3. Individuals predicted to incur high expenditures |
600 |
600 |
|
4. Low income |
2,126 |
1,274 |
|
5.Adults with other limitations |
326 |
194 |
|
6. Adults aged 65 and older |
2,163 |
652 |
|
7. Other |
8,770 |
2,678 |
|
Total |
15,067 |
6,480 |
Source: 1996 National Health Interview Survey, National Center for Health
Statistics, CDC Return To Table Of Contents
|
Table 3C: 1996 NHIS person level sample
classification available for MEPS |
|
Available Sample |
1997 MEPS Subsample |
|
Persons in dwelling units (hierarchically classified) with at least one
member |
1996 NHIS Frequency |
Frequency |
|
1. Functionally impaired adults |
506 |
506 |
|
2. Children with activity limitations |
723 |
723 |
|
3. Individuals predicted to incur high expenditures |
701 |
701 |
|
4. Low income |
6,304 |
4,181 |
|
5.Adults with other limitations |
393 |
253 |
|
6. Adults aged 65 and older |
3,234 |
1,109 |
|
7. Other |
26,557 |
9,590 |
|
Total |
38,418 |
17,063 |
Source: 1996 National Health Interview Survey, National Center for Health
Statistics, CDC Return To Table Of Contents
|
Table 3D 1996 NHIS person level sample selected for
MEPS |
| |
1997 MEPS Subsample |
|
Individuals with the following characteristics (a person may be
classified in more than one category) |
Frequency |
|
1. Functionally impaired adults |
506 |
|
2. Children with activity limitations |
723 |
|
3. Individuals predicted to incur high expenditures |
755 |
|
4. Low income |
7,990 |
|
5.Adults with other limitations |
900 |
|
6. Adults aged 65 and older |
4,600 |
Source: 1996 National Health Interview Survey, National Center for Health
Statistics, CDC Return To Table Of Contents
4.0 Procedures for Data Collection
The preliminary contact with households responding to NHIS
and subsampled as part of a MEPS panel is described in S. Cohen (1997).
Procedures in the rounds of data collection are described below.
Rounds 1-5
Five interviews are conducted with each NHIS panel selected
for MEPS at 4- to 5-month intervals over an approximately 24-month field period.
The first three rounds (Panel 1:Rounds 1-3) define the 1996 MEPS Household
Component and collect the main body of annual use and expenditure data for
calendar year 1996. Rounds 3-5 of the 1996 MEPS panel (Panel 1: Rounds 3-5) are
combined with Rounds 1-3 of the 1997 MEPS panel (Panel 2:Rounds 1-3) to yield
the sample base for the 1997 MEPS Household Component and the source of annual
estimates for that calendar year. All interviews are conducted in person through
a computer-assisted personal interview (CAPI). Round 1 asks about the period
from January 1 of the MEPS year to the date of that interview; Round 2 will ask
about the time from the Round 1 interview through the date of the Round 2
interview, and Round 3 asks about the time from the date of the Round 2
interview through the date of the Round 3 interview in 1997.
Questionnaires for these field rounds parallel those used in
the 1987 NMES but include some modifications implemented for a 1992 feasibility
study and further changes stemming from the feasibility study and the NMES-3
pretest. The instruments contain items that are asked once in the life of the
study, items that are asked repeatedly in each round, and items that are updated
in later rounds. Questions asked only once include basic sociodemographic
characteristics. Core questions asked repeatedly include health status, health
insurance coverage, employment status, days of restricted activity due to health
problems, medical use, hospital admissions, and purchase of medicines. For each
health encounter identified, data are obtained on the nature of health
conditions, characteristics of the provider, services provided, associated
charges, and sources and amounts of payment.
Permission forms for medical are collected in the field. A
sample of medical providers identified by MEPS respondents is contacted in the
survey of medical providers (the Medical Provider Component (MPC) of MEPS), to
verify and supplement information provided by the family respondent in the
household interview. Employers and other health insurance providers are
contacted in the survey of health insurance providers (the Insurance Component
(IC) of the MEPS), to collect other information on insurance characteristics
that household respondents would not typically know. Return To Table Of Contents
5.0 Sample Yields for the 1997 MEPS and Survey Response Rates
Data are collected for each MEPS panel to cover a two-year
period, with the first two MEPS panels spanning 1996-97 and 1997-98,
respectively. This section provides a summary of the sample yields for the
deriving national person based estimates from the 1997 MEPS, for both point in
time estimates (first part of calendar year 1997) and annual estimates.
Attention will first be given to the point in time estimation capacity of the
survey, followed by an emphasis on the sample yields for producing calendar year
health care estimates from the survey.
To produce point in time health care estimates for the first
part of 1997 based on the MEPS sample design, data will need to be pooled from
the first two MEPS national samples, with data covering approximately the first
half of calendar year 1997. More specifically, data from the 1997 portion of the
third round of data collection for the MEPS Panel 1 sample are pooled with
data from the first round of data collection for the MEPS Panel 2 sample
(illustrated below). This feature of the MEPS design supports the derivation of
health insurance coverage estimates covering the first half of calendar year
1997.
Return To Table Of Contents
Point in Time Estimates Covering First Part of 1997
301 Moved Permanently
301 Moved Permanently
MEPS Panel 1
The MEPS Panel 1 sample initially consisted of a sample of
10,639 households in 1996, a nationally representative subsample of the
households responding to the 1995 National Health Interview Survey (NHIS). The
1995 NHIS sampled households with Hispanic members and households with Black
members at approximately 2.0 and 1.5 times the rate of other households,
respectively. These oversampling rates are also reflected in the MEPS sample of
households. The 1995 NHIS response rate achieved for MEPS-eligible households
was 94 percent. Of 10,639 responding NHIS dwelling units eligible for MEPS, 99.6
percent were identified with enough information to allow MEPS data collection.
Of the 11,424 eligible reporting units targeted for interviews in Round 1, 9,488
(83.1 percent) responded. Overall, the joint NHIS-Round 1 response rate for the
1996 MEPS household survey was 77.7 percent (.939 x .996 x .831). Conditioned on
participation in the MEPS, 90.33 percent of the sample participants provided
data for their entire period of eligibility in 1996 and through the early part
of 1997 (Round 3). Consequently, the overall MEPS Panel 1 response rate at the
end of round 3 (which collects data for the first part of 1997) was 70.2
percent, reflecting response to the 1995 NHIS interview and the MEPS interviews
for rounds 1-3 (S. Cohen, 1997). Overall, the Round 3 MEPS Panel 1 sample
consisted of 21,411 survey participants.
Panel 2
The 1997 MEPS Panel 2 sample initially consisted of a sample
of 6,300 eligible NHIS dwelling units serving as a nationally
representative subsample of the households responding to the NHIS. As for Panel
1, the Panel 2 sample reflects the oversampling of Hispanic and Black households
in the NHIS. However, the sample allocation for Panel 2 of the MEPS
differed from that for Panel 1 because of the additional oversampling of the
targeted policy relevant groups. The 1996 NHIS response rate achieved for
MEPS-eligible households was 93.8 percent. Of the 6,196 eligible dwelling units
targeted for interviews in Round 1, 5,182 responded, consisting of 5,536
responding reporting units (.831). The overall MEPS Panel 2 response rate at the
end of round 1 (when data were collected for the first part of 1997) was 77.9
percent. This overall rate reflects response to both the 1996 NHIS interview and
the MEPS round 1 interview, consisting of a total sample of 14,505 survey
participants. Return To Table Of Contents
Combined
MEPS Response Rates for Point in Time 1997 Estimates (first half of year)
Each panel was given equal weight in the development of
sampling weights to produce national estimates. Therefore, a pooled response
rate for the survey respondents in this data set can be obtained by taking an
average of the panel specific response rates. This pooled response rate for the
combined panels is 74.1 percent, consisting of a total of 35,916 survey
participants within 14,147 family and single person analytical units in MEPS.
The weighted MEPS population estimate for the civilian non-institutionalized
population as of March 1997 was 265,926,692, based on poststratification to
population estimates produced from the March 1997 Current Population Survey. The
weighted estimate of the number of family units (family and single person units)
as of March 1997 was 112,106,153, based on data from the same source.
Using data from the 1997 MEPS Panel 1 Round 3/Panel 2 Round 1
Public Use file, population estimates of the proportion of the population that
was uninsured was produced for the overall population and for a representative
set of analytical domains, which included several of the population subgroups
targeted for oversampling (Table 4). The low income and high expenditure
population subgroups were not included in this analyses as a consequence of the
unavailability of the 1997 MEPS full year data at the time of this publication.
The table includes sample yields for the full 1997 MEPS sample, in addition to
the level of precision achieved for the survey estimates as measured by the
relative standard error and the respective survey design effects.
The 1997 MEPS point in time sample includes an oversample of
minorities, with 7,960 Hispanic sample participants and 5,301 Black,
Non-Hispanic sample participants, which reflects the oversampling rates for
minorities inherent in the NHIS sample (Hispanics, 2.0:1; blacks, 1.5:1).
Alternatively, the overall sample yield for the elderly, consisting of 4,104
sample participants and 11.4 percent of the sample, is quite consistent with
their proportional representation in the population, as anticipated by the MEPS
sample selection rates applied to the eligible NHIS sample.
As can be observed in Table 4, the sample yields achieved for
the pooled 1997 MEPS point in time sample were consistent with targeted sample
yields for the full year 1997 MEPS after adjusting for survey. After factoring
in the anticipated sample size reductions attributable to survey attrition for
the point in time 1997 estimates of the uninsured, it is evident that precision
levels for the full year 1997 MEPS were largely realized when considering
comparable population estimates. It should be noted that some of the estimates
of the uninsured obtained from the 1997 MEPS were less than 20 percent (the
value used to set precision targets), which would partially explain some of the
observed differentials from the precision targets, which were also specified as
average relative standard errors. Return To Table Of Contents
|
Table 4: 1997 MEPS Sample Yields |
1996 |
1997 |
Pooled (Panels 1 and 2) |
|
Demographic Subgroup |
Unweighted Sample |
Unweighted Sample |
Unweighted Sample |
% Uninsured |
Standard Error (%) |
Relative SE (%) |
Design Effect |
|
Overall Population |
21,411 |
14,505 |
35,916 |
16.76 |
0.389 |
2.321 |
3.89 |
|
Sex
Male
Female |
10,191
11,220 |
6,842
7,663 |
17,033
18,883 |
18.51
15.09 |
0.472
0.414 |
2.550
2.744 |
2.52
2.53 |
|
Race/ethnicity
Hispanic
Black-nonHispanic
Other |
4,610
2,879
13,922 |
3,350
2,422
8,733 |
7,960
5,301
22,655 |
32.94
21.45
13.63 |
1.118
0.985
0.392 |
3.394
4.592
2.876 |
4.51
3.05
2.95 |
|
Age
Under 6
6-17
18-44
45-64
65 and older |
1,989
4,265
8,296
4,392
2,469 |
1,450
3,160
5,428
2,832
1,635 |
3,439
7,425
13,724
7,224
4,104 |
14.27
15.72
23.36
14.84
1.02 |
0.895
0.679
0.579
0.587
0.194 |
6.272
4.319
2.479
3.956
19.020 |
2.25
2.58
2.57
1.97
1.53 |
|
Activity Limitations |
|
|
|
|
|
|
|
|
1+ADL (18 yrs and older) |
292 |
346 |
638 |
4.81 |
4.137 |
23.638 |
1.80 |
|
1+IADL (18 yrs and older) |
528 |
603 |
1,131 |
5.97 |
0.937 |
15.695 |
1.77 |
|
Region
Northeast
Midwest
South
West |
4,238
4,637
7,442
5,094 |
2,752
2,941
5,150
3,662 |
6,990
7,578
12,592
8,759 |
14.20
12.51
19.62
18.93 |
0.639
0.728
0.745
0.921 |
4.500
5.819
3.797
4.865 |
2.34
3.67
4.43
4.84 |
Source: 1997 MEPS, Center for Cost and Financing Studies, Agency for
Healthcare Research and Quality. Return To Table Of Contents
More specifically, there were 638 adults in the MEPS who
received help or supervision with activities of daily living (ADLs), which
included bathing, dressing or getting around the house, because of an impairment
or a physical or mental problem (Table 4). This subset of activities of daily
living is less inclusive than the set of ADLs considered in the NHIS for
oversampling purposes, and indicates the lower bound in terms of sample size
yields for this target population. In addition, a design effect of 1.8 was
achieved for the survey estimate of the uninsured that characterizes this policy
relevant population subgroup. There were also 1,131 adults in the MEPS who
received help or supervision with instrumental activities of daily living
(IADLs), which included using the telephone, paying bills, taking medications,
preparing light meals, doing laundry, or going shopping, because of an
impairment or a physical or mental problem (Table 4). This sample yield is
convergent with sample size targets for this policy relevant population
subgroup. A survey design effect of 1.8 was achieved for the associated survey
estimate of the percent of the population. An examination of the efficacy of the
sample design to achieve design goals for children with physical impairments,
households with low incomes and individuals with high levels of medical
expenditures will also be undertaken, to better inform future oversampling
efforts in MEPS for these target population subgroups, once the expenditure and
income data for the MEPS 1997 are available. A similar analysis will be
conducted to examine the level of precision realized for survey estimates of
health care utilization and expenditures, once the use and expenditure data for
the 1997 MEPS are available.
Annual Estimates for Calendar Year 1997
In order to produce annual health care estimates for calendar
year 1997 based on the full MEPS sample, data will also need to be pooled across
the first two MEPS national samples. More specifically, full calendar year 1997
data collected in Rounds 3 through 5 for the MEPS Panel 1 sample are pooled with
data from the first three rounds of data collection for the MEPS Panel 2 sample
(illustrated below). Overall, the full 1997 MEPS household sample will consist
of approximately 13,000 reporting units which include 32,636 individuals that
completed the full series of MEPS interviews for their entire period of
eligibility, providing the necessary information to produce national use and
expenditure estimates for calendar year 1997.
Panel 1
Conditioned on response to Rounds 1-3 of the Panel 1 MEPS, of
21,696 key and inscope individuals eligible for data collection in 1997, 19,622
(90.44 percent) provided data for their entire period of eligibility.
Consequently, after factoring in the impact of survey attrition, the overall
Panel 1 MEPS person level response rate for deriving annual estimates was 63.5
percent (.702 x .9044). Of these full year respondents for calendar year 1997,
19,407 were in scope on December 31, 1997.
Panel 2
Conditioned on response to Round 1 of the Panel 2 MEPS, of
14, 644 key and inscope individuals eligible for data collection in 1997, 13,014
( 88.87 percent) provided data for their entire period of eligibility.
Consequently, after factoring in the impact of survey attrition, the overall
Panel 2 MEPS person level response rate for deriving annual estimates was 69.2
percent (.779 x .8887). Of these full year respondents for calendar year 1997,
12,819 were in scope on December 31, 1997.
Combined MEPS Panels: Response Rate for Annual 1997 Estimates
Each panel was given equal weight in the development of
sampling weights to produce annual national estimates. Therefore, a pooled
response rate for the survey respondents in this data set can be obtained by
taking an average of the panel specific response rates. This pooled response
rate for the combined panels is 66.4 percent, consisting of a total of 32,636
survey participants. The weighted MEPS population estimate for the civilian
non-institutionalized population as of December 31, 1997 was 267,704,802, based
on poststratification to population estimates produced from the December 1997
Current Population Survey. Sample yields for the subset of the 32,636
survey participants that were in scope as of 12/31/97 (32,226) are presented in
Table 5, controlling for gender, race/ethnicity, region, MSA status and age.
|
Table 5: 1997 MEPS, Panels I and II combined, sample yields for full
year respondents as of 12/31/97 |
| |
Unweighted MEPS count |
Weighted CPS count |
|
Sex |
|
|
|
Male
Female |
15,239
16,987 |
130,734,620
136,970,181 |
|
Race/Ethnicity |
|
Hispanic
Non-Hispanic black
Other |
7,440
4,743
20,043 |
30,680,491
33,578,472
203,445,838 |
|
Region |
|
Northeast
Midwest
South
West |
6,144
6,763
11,309
8,010 |
51,118,238
62,426,339
93,820,483
60,339,742 |
|
Metropolitan Status |
|
MSA
NonMSA |
25,119
7107 |
215,387,710
52,317,091 |
|
Age |
|
Under 1
1 to 4 years old
5 to 9 years old
10 to 14 years old
15 to 19 years old
20 to 24 years old
25 to 29 years old
30 to 34 years old
35 to 44 years old
45 to 54 years old
55 to 59 years old
60 to 64 years old
65 to 69 years old
70 to 74 years old
75 to 79 years old
80 years old and older |
479
2,028
2,854
2,807
2,532
1,913
1,998
2,335
4,963
3,963
1,419
1,198
1,046
1017
776
898 |
3,819,437
15,840,700
20,404,149
19,563,172
19,452,449
17,531,979
18,827,116
20,322,814
44,120,234
33,907,056
11,896,295
9,956,233
9,413,817
8,532,698
6,842,152
7,274,502 |
|
Major Age Categories |
|
Under 1
1 to 19 years old
20 to 29 years old
30 to 44 years old
45 to 64 years old
65 years old and older |
479
10,221
3,911
7,298
6,580
3,737 |
3,819,437
75,260,469
36,359,095
64,443,048
55,759,584
32,063,169 |
|
Total |
32,226 |
267,704,802 |
|
Note: The MEPS sample size yields presented in this
table represents the population as of 12/31/97. |
|
When the full year MEPS sample of all persons with
positive person weight are included, the total MEPS respondent sample is
32,636 |
Return To Table Of Contents
6.0 Summary
This report has provided a summary of the sample design
features of the 1997 Household Component of the Medical Expenditure Panel
Survey. Particular attention has been given to the sample selection scheme
implemented for the new 1997 MEPS sample panel. The report also provides a
summary of the precision specifications for the survey, sample yields and the
level of precision in survey estimates. The details of the probabilistic models
that were used to select an expected oversample of low income households and for
individuals likely to incur high levels of medical expenditures in 1997 were
also presented, in addition to measures of the predictive capacity of the
respective models. Both the panel specific and pooled survey response rates were
also summarized for the 1997 MEPS Panel 1 Round 3/Panel 2 Round 1 point in time
sample (first half of 1997) and for annual estimates.
The MEPS data also serve as the primary source of information
for research efforts examining how health care use and expenditures vary among
different sectors of the population (such as the elderly, veterans, children,
disabled persons, minorities, the poor, and the uninsured) and how the health
insurance of individuals varies by demographic characteristics, employment
status and characteristics, geographic locale, and other factors. The MEPS data
are and will continue to provide answers to questions about private health
insurance costs and coverage, and help evaluate the growing impact of managed
care on health care expenditures and enrollment in different types of managed
care plans.
7.0 References
Arnett RA, Hunter E, Cohen S, et al. The Department of Health
and Human Services' Survey Integration Plan. In: Proceedings of the American
Statistical Association (ASA). Section on Government Statistics. Chicago: 1996
Aug.
Cohen J. Design and Methods of the Medical Expenditure Panel
Survey Household Component. Rockville (MD): Agency for Health Care Policy and
Research; 1997. MEPS Methodology Report No. 1. AHCPR Pub. No. 97-0026.
Cohen, S.B. Sample Design of the 1996 Medical Expenditure
Panel Survey Household Component. Rockville (MD): Agency for Health Care Policy
and Research, 1997. MEPS Methodology Report No. 2. AHCPR Pub. No. 97-0027.
Cohen SB. The redesign of the Medical Expenditure Panel
Survey, a component of the DHHS Survey Integration Plan. Proceedings of the
Council of Professional Associations on Federal Statistics (COPAFS) Seminar on
Statistical Methodology in the Public Service, Bethesda (MD); 1996 Nov.
DiGaetano R. Sample design of the Household Component of the
National Medical Expenditure Survey (NMES-3). Unpublished report. Rockville
(MD): Westat, Inc.; 1994. Contract No. 282-94-200.
Hunter E, Arnett R, Cohen S, et al. HHS Survey Integration
Plan: Background materials. Agency for Health Care Policy and Research,
Rockville (MD), and National Center for Health Statistics, Hyattsville (MD);
1995.
Judkins D, Marker D, Waksberg J. National Health Interview
Survey: research for the 1995 redesign. Unpublished report. Prepared under
contract for the National Center for Health Statistics. Rockville (MD): Westat,
Inc.; 1994.
Moeller, J and Mathiowetz, N. Internal Memos on Low Income
and High Expenditure Prediction Models; 1994. Return To Table Of Contents
Appendix 3:
Summary of Utilization and Expenditure Variables by Health Service Category
|
HEALTH SERVICE CATEGORY |
UTILIZATION VARIABLE(S) |
EXPENDITURE VARIABLE(S) |
|
All Health Services |
-- |
TOT***97 |
|
Office Based Visits |
|
|
|
Total Office Based Visits (Physician + Non-physician + Unknown) |
OBTOTV97 |
OBV***97 |
|
Office Based Visits to Physicians |
OBDRV97 |
OBD***97 |
|
Office Based Visits to Non-Physicians |
OBOTHV97 |
OBO***97 |
|
Office Based Visits to Chiropractors |
OBCHIR97 |
OBC***97 |
|
Office Based Nurse or Nurse Practitioner Visits |
OBNURS97 |
OBN***97 |
|
Office Based Visits to Optometrists |
OBOPTO97 |
OBE***97 |
|
Office Based Physician Assistant Visits |
OBASST97 |
OBA***97 |
|
Office Based Physical or Occupational Therapist Visits |
OBTHER97 |
OBT***97 |
|
Hospital Outpatient Visits |
|
|
|
Total Outpatient Visits (Physician + Non-physician + Unknown) |
OPTOTV97 |
-- |
|
Facility Expense |
-- |
OPF***97 |
|
SBD Expense |
-- |
OPD***97 |
| |
|
|
|
Outpatient Visits to Physicians |
OPDRV97 |
-- |
|
Facility Expense |
-- |
OPV***97 |
|
SBD Expense |
-- |
OPS***97 |
| |
|
|
|
Outpatient Visits to Non-Physicians |
OPOTHV97 |
-- |
|
Facility Expense |
-- |
OPO***97 |
|
SBD Expense |
-- |
OPP***97 |
Return To Table Of Contents
|
HEALTH SERVICE CATEGORY |
UTILIZATION VARIABLE(S) |
EXPENDITURE VARIABLE(S) |
|
Emergency Room Visits |
|
|
|
Total Emergency Room Visits |
ERTOT97 |
-- |
|
Facility Expense |
-- |
ERF***97 |
|
SBD Expense |
-- |
ERD***97 |
|
Inpatient Hospital Stays (Including Zero Night Stays) |
|
|
|
Total Inpatient Stays (Including Zero Night Stays) |
IPDIS97, IPNGTD97 |
-- |
|
Facility Expense |
-- |
IPF***97 |
|
SBD Expense |
-- |
IPD***97 |
| |
|
|
|
Zero night Hospital Stays |
IPZERO97 |
-- |
|
Facility Expense |
-- |
ZIF***97 |
|
SBD Expense |
-- |
ZID***97 |
|
Dental Visits |
|
|
|
Total Dental Visits |
DVTOT97 |
DVT***97 |
|
General Dental Visits |
DVGEN97 |
DVG***97 |
|
Orthodontist Visits |
DVORTH97 |
DVO***97 |
|
Home Health Care |
|
|
|
Total Home Health Care |
HHTOTD97 |
-- |
|
Agency Sponsored |
HHAGD97 |
HHA***97 |
|
Paid Independent Providers |
HHINDD97 |
HHN***97 |
|
Informal |
HHINFD97 |
-- |
|
Other |
|
|
|
Vision Aids |
-- |
VIS***97 |
|
Other Medical Supplies and Equipment |
-- |
OTH***97 |
|
Prescription Medicines |
RXTOT97 |
RX***97 |
KEY: To complete variable name, replace *** with a particular source of
payment category as identified in the following table: Return To Table Of Contents
|
Source of Payment Category |
*** |
|
Total payments (sum of all sources) |
EXP |
|
Out of Pocket |
SLF |
|
Medicare |
MCR |
|
Medicaid |
MCD |
|
Private Insurance |
PRV |
|
Veteran’s Administration |
VA |
|
CHAMPUS or CHAMPVA |
CHM |
|
Other Federal Sources |
OFD |
|
Other State and Local Sources |
STL |
|
Workers’ Compensation |
WCP |
|
Other Private |
OPR |
|
Other Public |
OPU |
|
Other Unclassified Sources |
OSR |
|
Total charges |
TCH |
Return To Table Of Contents
Return to the MEPS Homepage
|
Back
Email Updates
