September 2019
Agency for Healthcare Research and Quality
Center for Financing, Access, and Cost Trends
5600 Fishers Ln
Rockville, MD 20857
(301) 427-1406
NOTE: The MEPS instrument design changed beginning in
Spring of 2018, affecting Panel 23 Round 1, Panel 22 Round 3, and Panel 21 Round
5. For the Full-Year 2017 PUFs, the Panel 22 Round 3 and Panel 21 Round 5 data
were transformed to the degree possible to conform to the previous design.
Data users should be aware of possible impacts on the data and especially
trend analysis for these data years due to the design transition.
TABLE OF CONTENTS
A. Data Use Agreement
B. Background
B.1 Household Component
B.2 Medical Provider Component
B.3 Survey Management and Data Collection
C. Technical and Programming Information
C.1 General Information
C.2 Data File Information
C.2.1 Variables
C.2.1.1 Variables from Annual Full-year Consolidated Files
C.2.1.2 Constructed Variables for Selection of Group
C.2.1.3 Estimation Variables
Individual identifiers have been removed from the micro data contained in these files. 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 Healthcare Research and Quality (AHRQ) and/or the National Center for Health Statistics (NCHS)
may not be used for any purpose other than for the purpose for which they were 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 AHRQ will be advised of this incident, (c) the
information that would identify any individual or establishment will be safeguarded or destroyed, as requested
by AHRQ, and (d) no one else will be informed of the discovered identity; and
- 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 these 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 Title 18 part 1 Chapter 47 Section 1001 and is
punishable by a fine of up to $10,000 or up to 5 years in prison.
The Agency for Healthcare Research and Quality requests that users cite AHRQ and the Medical Expenditure Panel
Survey as the data source in any publications or research based upon these data.
Return To Table Of Contents
The Medical Expenditure Panel Survey (MEPS) provides nationally representative estimates of healthcare use,
expenditures, sources of payment, and health insurance coverage for the U.S. civilian non-institutionalized
population. The MEPS Household Component (HC) also provides estimates of respondents' health status, demographic and
socio economic characteristics, employment, access to care, and satisfaction with health care. Estimates can be produced
for individuals, families, and selected population sub-groups. The panel design of the survey, which includes 5 Rounds
of interviews covering 2 full calendar years, provides data for examining person level changes in selected variables
such as expenditures, health insurance coverage, and health status. Using computer assisted personal interviewing
(CAPI) technology, information about each household member is collected, and the survey builds on this information
from interview to interview. All data for a sampled household are reported by a single household respondent.
The MEPS-HC was initiated in 1996. Each year a new panel of sample households is selected. Because the data collected
are comparable to those from earlier medical expenditure surveys conducted in 1977 and 1987, it is possible to analyze
long-term trends. Each annual MEPS HC sample size is about 15,000 households. Data can be analyzed at either the person
or event level. Data must be weighted to produce national estimates.
The set of households selected for each panel of the MEPS HC is a subsample of households participating in the
previous year's National Health Interview Survey (NHIS) conducted by the National Center for Health Statistics. The
NHIS sampling frame provides a nationally representative sample of the U.S. civilian noninstitutionalized
population and reflects an oversample of blacks and Hispanics. In 2006, the NHIS implemented a new sample design,
which included Asian persons in addition to households with black and Hispanic persons in the oversampling of
minority populations. MEPS further oversamples additional policy relevant sub-groups such as low income households.
The linkage of the MEPS to the previous year’s NHIS provides additional data for longitudinal analytic purposes.
Return To Table Of Contents
Upon completion of the household CAPI interview and obtaining permission from the household survey respondents,
a sample of medical providers are contacted by telephone to obtain information that household respondents cannot
accurately provide. This part of the MEPS is called the Medical Provider Component (MPC) and information is
collected on dates of visit, diagnosis and procedure codes, charges and payments. The Pharmacy Component (PC), a
subcomponent of the MPC, does not collect charges or diagnosis and procedure codes but does collect drug detail
information, including National Drug Code (NDC) and medicine name, as well as date filled and sources and amounts
of payment. The MPC is not designed to yield national estimates. It is primarily used as an imputation source
to supplement/replace household reported expenditure information.
Return To Table Of Contents
MEPS HC and MPC data are collected under the authority of the Public Health Service Act. Data are collected
under contract with Westat, Inc. Data sets and summary statistics are edited and published in accordance with
the confidentiality provisions of the Public Health Service Act and the Privacy Act. The National Center for
Health Statistics (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, micro data files, and tables via the MEPS website:
https://meps.ahrq.gov. Selected data can be analyzed through MEPSnet, an on-line
interactive tool designed to give data users the capability to statistically analyze MEPS data in a menu driven
environment.
Additional information on MEPS is available from the MEPS project manager or the MEPS public use data manager
at the Center for Financing Access and Cost Trends, Agency for Healthcare Research and Quality, 5600 Fishers Ln,
Rockville, MD 20857 (301-427-1406).
Return To Table Of Contents
This documentation describes the Panel 21 longitudinal data file from the Medical Expenditure Panel
Survey Household Component (MEPS-HC). Released as an ASCII file (with related SAS, STATA, and SPSS programming
statements and data use information) and a SAS transport dataset, this public use file provides information
collected on a nationally representative sample of the civilian noninstitutionalized population of the
United States for the two-year period 2016-2017. The file contains 3,324 variables and has a logical record
length of 9,195 with an additional 2-byte carriage return/line feed at the end of each record.
This file consists of MEPS survey data obtained in Rounds 1-5 of MEPS Panel 21 and can be
used to analyze changes over a two-year period. Variables in the file pertaining to survey administration,
demographics, employment, health status, disability days, quality of care, patient satisfaction, health insurance
and medical care use and expenditures were obtained from the MEPS 2016 and 2017 Full-Year Consolidated Files
(HC-192 and HC-202, respectively).
The following documentation offers a brief overview of the contents and structure of the files and programming
information. A codebook of all the variables included in the Panel 21 data file is provided in a separate file
(H202CB.PDF). A database of all MEPS products released to date and a variable locator indicating the major MEPS
data items on public use files that have been released to date can be found on the MEPS
website: https://meps.ahrq.gov.
Return To Table Of Contents
This public use file contains records for 15,617 persons in Panel 21 who were respondents for the period they were
in-scope for the survey (i.e., a member of the civilian non-institutionalized population) during the two-year
period. Only persons with positive person-level weights (PERWT16F or PERWT17F) are included in the longitudinal PUF data.
Data are available for all five rounds for 92.4% of the cases (14,431). The remaining 7.6% (1,186 persons) do not
have data for one or more rounds but were in-scope for all rounds they participated in the survey. These persons
are those who were born, died, were in the military or an institution, or left the country during the two-year
period. In contrast, persons in the panel who participated in the survey for only part of the period they were
in-scope are not included in this file. To compensate for this attrition, adjustments were made in the construction of
the panel weight variable included in this file (LONGWT). The codebook provides both weighted and
unweighted frequencies for each variable on the data file. The LONGWT variable should be used to produce national
estimates for the two-year period.
Each MEPS panel can be linked back to the previous year's National
Health Interview Survey public use data files. For information on obtaining
MEPS/NHIS link files please see
https://meps.ahrq.gov/mepsweb/data_stats/more_info_download_data_files.jsp.
Return To Table Of Contents
Most variables on this file were obtained from the MEPS 2016 and 2017 Full-Year Consolidated Files (HC-192
and HC-202, respectively). However, names for time dependent variables from these files were modified in
order to: 1) eliminate duplicate variable names for data reflecting different time periods during the panel,
and 2) standardize variable names to facilitate pooling of multiple MEPS panels for analysis.1
Generally, annual variables with a suffix of “16” and “17” are renamed
with a suffix of “Y1” and “Y2”, respectively. Variables with a suffix of “31”,
“42”, and “53” are renamed with a suffix denoting the round the data was collected
(i.e., “1” , “2” or “3” for variables originating from Rounds 1-3 on
the 2016 full-year file and “3”, “4”, or “5” for variables originating
from Rounds 3-5 on the 2017 full-year file).2 It is necessary to use
this crosswalk in conjunction with documentation for the 2016 and 2017 full-year consolidated files to
obtain a full description of variables on this file. Table 1 below provides the crosswalk summarizing the
scheme used for renaming variables from the annual files.
Return To Table Of Contents
Table 1: Crosswalk of Variable Names between the Full-Year Consolidated Files and the Longitudinal File
| Type of Variable |
Full-Year Consolidated File Variable Name Suffix |
Longitudinal File Variable Name Suffix |
Specific cases or examples |
| Constant (i.e., not round or year specific) |
No suffixes |
No suffixes |
All variables:
DOBMM=DOBMM
DOBYY=DOBYY
DUID=DUID
PID=PID
DUPERSID=DUPERSID
EDUCYR=EDUCYR
HIDEG=HIDEG
HISPANX=HISPANX
HISPNCAT=HISPNCAT
INTVLANG=INTVLANG
RACEAX=RACEAX
RACEBX=RACEBX
RACEWX=RACEWX
RACEV1X=RACEV1X
RACEV2X=RACEV2X
RACETHX=RACETHX
SEX=SEX
VARPSU=VARPSU
VARSTR=VARSTR
PANEL=PANEL
BORNUSA=BORNUSA
HWELLSPE=HWELLSPE
LANGSPK=LANGSPK
OTHLANG=OTHLANG
YRSINUS=YRSINUS
|
| Annual, family related variables |
YR |
Y1 or YR1 |
All variables:
FAMIDYR=FAMIDYR1 (2016 file)
FAMRFPYR=FAMRFPY1 (2016 file)
FAMSZEYR=FAMSZYR1 (2016 file) |
| Y2 or YR2 |
All variables:
FAMIDYR=FAMIDYR2 (2017 file)
FAMRFPYR=FAMRFPY2 (2017 file)
FAMSZEYR=FAMSZYR2 (2017 file) |
| Annual, CPS family identifiers |
No suffix |
Y1 |
All variables:
CPSFAMID=CPSFAMY1 (2016) |
| Y2 |
All variables:
CPSFAMID=CPSFAMY2 (2017) |
| Annual, health insurance eligibility units |
No suffix |
Y1 |
All variables:
HIEUIDX=HIEUIDY1 (2016) |
| Y2 |
All variables:
HIEUIDX=HIEUIDY2 (2017) |
| Annual, inscope variables |
No suffixes |
YR1 |
All variables:
INSCOPE=INSCPYR1 (2016 file) |
| YR2 |
All variables:
INSCOPE=INSCPYR2 (2017 file) |
| 12/31 status variables |
1231 in 2016 file |
Y1 |
All variables:
FAMS1231=FAMSY1 (2016 file)
FCRP1231=FCRPY1 (2016 file)
FCSZ1231=FCSZY1 (2016 file)
FMRS1231=FMRSY1 (2016 file)
INSC1231=INSCY1 (2016 file) |
| 1231 in 2017 file |
Y2 |
All variables:
FAMS1231=FAMSY2 (2017 file)
FCRP1231=FCRPY2 (2017 file)
FCSZ1231=FCSZY2 (2017 file)
FMRS1231=FMRSY2 (2017 file)
INSC1231=INSCY2 (2017 file) |
| Annual |
16, 16X, 16F, or 16C |
Y1, Y1X, Y1F, or Y1C |
Examples:
TOTEXP16=TOTEXPY1
AGE16X=AGEY1X |
| 17, 17X, 17F, or 17C |
Y2, Y2X, Y2F, or Y2C |
Examples:
TOTEXP17=TOTEXPY2
AGE17X=AGEY2X |
| Variables for health insurance prior to
January 1, 2016 (data collected in round 1 only) |
No suffixes |
No suffixes |
All variables:
PREVCOVR=PREVCOVR
COVRMM=COVRMM
COVRYY=COVRYY
WASESTB=WASESTB
WASMCARE=WASMCARE
WASMCAID=WASMCAID
WASCHAMP=WASCHAMP
WASVA=WASVA
WASPRIV=WASPRIV
WASOTGOV=WASOTGOV
WASAFDC=WASAFDC
WASSSI=WASSSI
WASSTAT1=WASSTAT1
WASSTAT2=WASSTAT2
WASSTAT3=WASSTAT3
WASSTAT4=WASSTAT4
WASOTHER=WASOTHER
NOINSBEF=NOINSBEF
NOINSTM=NOINSTM
NOINUNIT=NOINUNIT
MORECOVR=MORECOVR
INSENDMM=INSENDMM
INSENDYY=INSENDYY |
| Annual |
No suffixes3 |
Y1 |
All variables:
KEYNESS=KEYNESY1 (2016 file)
SAQELIG=SAQELIY1 (2016 file)
EVRWRK=EVRWRKY1 (2016 file)
EVRETIRE=EVRETIY1 (2016 file)
AGELAST=AGELSTY1 (2016 file) |
| Y2 |
All variables:
KEYNESS=KEYNESY2 (2017 file)
SAQELIG=SAQELIY2 (2017 file)
EVRWRK=EVRWRKY2 (2017 file)
EVRETIRE=EVRETIY2 (2017 file)
AGELAST=AGELSTY2 (2017 file) |
| Monthly |
2-character month + 16 |
2-character month + Y1 |
Examples:
PRIJA16=PRIJAY1 (2016 file) |
| 2-character month + 17 |
2-character month + Y2 |
Examples:
PRIJA17=PRIJAY2 (2017 file) |
| Round Specific |
31, 31X, or 31H in 2016
42, 42X, or 42H in 2016
53, 53X, or 53H in 2016 |
1, 1X, 1H for 2016
2, 2X, 2H for 2016
3, 3X, 3H for 2016 |
Examples:
RTHLTH31=RTHLTH1 (2016 file)
RTHLTH42=RTHLTH2 (2016 file)
RTHLTH53=RTHLTH3 (2016 file if YEARIND=2) |
31, 31X, or 31H in 2017
42, 42X, or 42H in 2017
53, 53X, or 53H in 2017 |
3, 3X, 3H for 2017
4, 4X, 4H for 2017
5, 5X, 5H for 2017 |
Examples:
RTHLTH31=RTHLTH3 (2017 file if YEARIND=1 or 3)
RTHLTH42=RTHLTH4 (2017 file)
RTHLTH53=RTHLTH5 (2017 file) |
| Diabetes preventive care |
1553, 1653, and 1753 in 2016 file |
Y0R3 for 2015
Y1R3 for 2016
Y2R3 for 2017 |
Examples:
DSEB1553=DSEBY0R3 (2016 file)
DSEY1553=DSEYY0R3 (2016 file)
DSEY1653=DSEYY1R3 (2016 file)
DSEY1753=DSEYY2R3 (2016 file) |
| 1653, 1753, and 1853 in 2017 file |
Y1R5 for 2016
Y2R5 for 2017
Y3R5 for 2018 |
Examples:
DSEB1653=DSEBY1R5 (2017 file)
DSEY1653=DSEYY1R5 (2017 file)
DSEY1753=DSEYY2R5 (2017 file)
DSEY1853=DSEYY3R5 (2017 file) |
| Job Change |
3142
4253 |
12 for 2016
23 for 2016 |
All cases:
CHGJ3142=CHGJ12 (2016 file)
CHGJ4253=CHGJ23 (2016 file)
YCHJ3142=YCHJ12 (2016 file)
YCHJ4253=YCHJ23 (2016 file) |
34 for 2017
45 for 2017 |
All cases:
CHGJ3142=CHGJ34 (2017 file)
CHGJ4253=CHGJ45 (2017 file)
YCHJ3142=YCHJ34 (2017 file)
YCHJ4253=YCHJ45 (2017 file) |
| Cancer/Cancer in remission4 |
No suffixes5 |
Y1 for 2016 |
Example:
CALUNG=CALUNGY1 (2016 file)
|
| Y2 for 2017 |
Example:
CALUNG=CALUNGY2 (2017 file)
|
| Age of Diagnosis |
No suffixes5 |
Y1 for 2016 |
Example:
CHDAGED=CHDAGY1 (2016 file)
CHOLAGED=CHOLAGY1 (2016 file) |
| Y2 for 2017 |
Example:
CHDAGED=CHDAGY2 (2017 file)
CHOLAGED=CHOLAGY2 (2017 file) |
Return To Table Of Contents
The following eight variables were
constructed and included on the file to facilitate the selection of
appropriate cases for various analyses. Table 2 below contains descriptive
statistics for these variables.
| YEARIND |
1=both years, 2=in 2016 only, and
3=in 2017 only |
| ALL5RDS |
Inscope and data collected in all 5
rounds (0=no, 1=yes) |
| DIED |
Died during the two-year survey
period (0=no, 1=yes) |
| INST |
Institutionalized for some time during
the two-year survey period (0=no, 1=yes) |
| MILITARY |
Active duty military for some time
during the two-year survey period (0=no, 1=yes) |
| ENTRSRVY |
Entered survey after beginning of panel
(mainly births; also includes persons
who had no initial chance of selection who
moved into a MEPS sample household) (0=no, 1=yes) |
| LEFTUS |
Moved out of the country after beginning
of panel (0=no, 1=yes) |
| OTHER |
Not identified in any of the above
analytic groups (0=no, 1=yes) |
Table 2: Frequencies and Percentage for Constructed Variables
| Variable |
Number of Records |
Percentage of Records (N=15,617) |
| YEARIND=1 (i.e., person in both years) |
15,252 |
97.7 |
| ALL5RDS=1 (yes) |
14,431 |
92.4 |
| DIED=1 (yes) |
185 |
1.2 |
| INST=1 (yes) |
44 |
0.3 |
| MILITARY=1 (yes) |
33 |
0.2 |
| ENTRSRVY=1 (yes) |
790 |
5.1 |
| LEFTUS=1 (yes) |
73 |
0.5 |
| OTHER=1 (yes) |
77 |
0.5 |
Following are examples of situations where these variables would be useful in selecting records for analysis:
- Analysts interested in working only with persons who were in-scope and had data for all five rounds of the panel
should subset to cases where ALL5RDS=1.
- If a researcher wanted to include persons who were in-scope and had data for all five rounds of the panel as
well as those in the survey at the beginning of the panel who subsequently died, then they would include cases
where ALL5RDS=1 or (ENTRSRVY=0 and DIED=1).
- If a researcher wanted to include persons who were in-scope and had data for all five rounds of the panel as
well as those who died in the second year of the panel, then they would include cases where ALL5RDS=1 or
(DIED=1 and YEARIND=1).
Return To Table Of Contents
Longitudinal Estimations for Panel 21
The file contains a weight variable (LONGWT) and variance estimation variables (VARSTR, VARPSU) that should be
applied when producing national estimates for longitudinal analyses. For example, LONGWT applied to the
14,431 cases where ALL5RDS=1 produces a weighted population estimate of 303.3 million. This represents an
estimate of the number of persons in the civilian noninstitutionalized population for the entire two-year period
from 2016-2017. To obtain estimates of variability (such as the standard error of sample estimates or corresponding
confidence intervals) for estimates based on MEPS survey data, one needs to take into account the complex sample
design of MEPS by specifying the estimation variables including stratum of sample selection (VARSTR),
primary sampling unit (VARPSU) and longitudinal weight (LONGWT).
This longitudinal file also contains a longitudinal SAQ weight variable (LSAQWT). This weight
variable should be used to perform longitudinal analyses involving any variables from the self-administered questionnaire (SAQ)
which was administered to persons age 18 and older in both rounds 2 and 4 of the survey. The variable SAQRDS24 can be used
to identify which persons have SAQ data for both versus only one of the two rounds. The estimated population size
(i.e. sum of LSAQWT values) for analyses based on the 9,486 cases with SAQ data for both rounds
(i.e., SAQRDS24=1) is 228,056,818.
Pooled Estimations
When analyzing subpopulations and/or low prevalence events, it may be desirable to pool together more than one
panel of MEPS-HC data to yield sample sizes large enough to generate reliable estimates. If only data
from Panels 7 and beyond are being pooled, then simply use the strata and PSU variables (VARSTR, VARPSU)
6 provided on the longitudinal files for pooled estimation. However, because
Panels 1-6 MEPS longitudinal weight files were released with panel-specific variance structures, it is
necessary to obtain the set of appropriate variance estimation variables from the HC-036 Pooled Estimation
File when pooling involves these panels.
1 A variable named PANEL is also included to facilitate
pooling across panels. This variable is simply the panel number and is therefore constant across all records within a
longitudinal file.
2 While round 3 values were obtained for most observations from the
2017 Full Year Consolidated File, they were obtained from the
20156 Full Year Consolidated File for sample persons where YEARIND=2 (i.e., in 2015 only).
3 To maintain the 8-character naming convention, some variable
names had the last character or two dropped in the renaming process.
4 Starting in 2010, variables were added to indicate
whether each reported cancer was in remission.
5 To maintain the 8-character naming convention, some
variable names had the last character or two dropped in the renaming process.
6 Note that variable names for strata and PSU are VARSTR
and VARPSU respectively in longitudinal files for panel 9 and beyond. These variables were named differently in the
longitudinal files for panel 7 (VARSTRP7, VARPSUP7) and panel 8 (VARSTRP8, VARPSUP8) and need to be standardized when
pooling with subsequent panels.
Return To Table Of Contents
|
Back
Email Updates
