MEPS HC-100: 2006 Jobs File
May 2008
Agency for Healthcare Research and Quality
Center for Financing, Access, and Cost Trends
540 Gaither Road
Rockville, MD 20850
(301) 427-1406

Table of Contents

A. Data Use Agreement
B. Background
1.0 Household Component
2.0 Medical Provider Component
3.0 Survey Management and Data Collection
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 Source and Naming Conventions
3.0 Pooling Annual Files
3.1 Longitudinal Analysis
3.2 Using MEPS Data for Trend Analysis
D. Variable-Source Crosswalk
Appendix 1: Sample SAS Program

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:

1. No one is to use the data in this data set in any way except for statistical reporting and analysis; and
    
2. 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
    
3. 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

B. Background

1.0 Household Component

The Medical Expenditure Panel Survey (MEPS) provides nationally representative estimates of health care 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 subgroups.  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 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 non-institutionalized population and reflects an oversample of blacks and Hispanics. MEPS oversamples additional policy relevant sub-groups such as Asians and 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

2.0 Medical Provider Component

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 can not 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

3.0 Survey Management and Data Collection

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 web site: www.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, 540 Gaither Road, Rockville, MD 20850 (301-427-1406).

Return To Table Of Contents

Section C of this document offers a brief overview of the data provided in MEPS public use release HC-100, as well as the content and structure of the codebook, reserved code values and variable naming conventions. It is followed by Section D containing the Variable-Source Crosswalk, and Appendix 1 containing sample SAS program code. A copy of the survey instrument used to collect the information on this file is available on the MEPS web site: www.meps.ahrq.gov.

Return To Table Of Contents

In the Employment section, MEPS collects complete job-related information in the round in which a job is first reported. While they vary by job type (see Section 3.0), the data reported for a job in its first survey round may include earnings by type (gross salary, tips, etc.), start and stop dates, hours and weeks worked, establishment size and industry, occupation, presence of retirement and other benefits, self-employment versus other status, temporary or seasonal situations, and health insurance availability. Minimal data updates are available for later rounds in which the job continues.

Each Full Year Jobs file contains job records from two MEPS panels. The Jobs file provided in this release, MEPS HC-100, contains job-level information collected in Rounds 3 through 5 for the tenth panel and Rounds 1 through 3 for the eleventh panel of the Medical Expenditure Panel Survey (i.e., the rounds for the MEPS panels covering calendar year 2006), as illustrated below.

In order to obtain complete information for a job, users must note the round in which the job is first reported. This is because MEPS collects complete Jobs information in that round only, as noted above.

For the first year panel, in this case Panel 11, data from Rounds 1, 2, and 3 are included in the Jobs file. Complete information for any Panel 11 job is available, whether that job was first reported in Round 1, 2, or 3. This is the case for any first year panel (the panel that began its first year of interviewing in the given year) in a Full-Year Jobs file.

For the second year panel (the panel that continued with its second year of interviewing in the given year), in this case Panel 10, data from Rounds 3, 4, and 5 are included in this file. If the Round 3, 4, or 5 job continued from Round 1 or 2, users must look back to the Jobs file from the previous year (2005) to obtain complete information for the job. Appendix 1 includes sample SAS code to assist users in obtaining this information. Users should note that, because of differences in sample composition between the current year and the previous year files (i.e. a person was included in the previous year’s delivery but not the current year or vice versa), or because more accurate information was received in Round 4 or 5 comments following the delivery of the Rounds 1 – 3 Jobs records in the previous year, there occasionally may not be a corresponding Round 1 or Round 2 job in the previous year file.

This file is being released as a research file and has not undergone the standard quality control procedures usually performed on MEPS data files. The file includes a total of 57,379records, with each record representing a unique job for a person by round. This file presents information about jobs starting on or before 12/31/2006 only. The 2007 MEPS Jobs file release will present information on Panel 11 jobs starting in 2007.

Return To Table Of Contents

Each record in the Jobs file represents one job reported by a person in a round. The unique record identifier is the variable JOBSIDX, which is comprised of a person identifier (DUID + PID), a round identifier (RN), and a job number (JOBSN). A panel indicator (PANEL) is included on the file to distinguish Round 3 jobs held by Panel 10 persons from Round 3 jobs held by those in Panel 11.

All persons age 16 and older in the MEPS are asked to report on jobs held. Depending on an individual’s job history, these reported jobs may be held:

• at the interview date,
• in the round but prior to the interview date, or
• prior to the round.

Only those persons reporting a job in a round will have a record on the Jobs file for that round.

Most persons held only one job at the first interview date – their "Current Main Job." Persons who held more than one job at the round’s interview date (a current job) were asked to identify the main job. This job was classified as the "Current Main Job" and any other simultaneously held job was classified as a "Current Miscellaneous Job." The MEPS also obtained some information on any former job (Former Main Job or Former Miscellaneous Job) held in the reference period but not at the interview date. For those persons neither working at the interview date nor earlier in the reference period, limited information on the last job the person held was collected. Additionally, for those persons age 55 or older who indicated that they retired from a job, the MEPS obtained some job-level information (Retirement Job).

The variable SUBTYPE indicates the type of job record - current main (1), current miscellaneous (2), former main (3), former miscellaneous (4), last job outside reference period (5), or retirement job (6). When a job is initially reported, MEPS asks for detailed information about any "Current Main Job" and "Current Miscellaneous Job" and basic information about other job types. Refer to the questionnaire to see which information was asked for each job type. It is important to note that the retirement job classification in the variable SUBTYPE is independent of the retirement response in the variable YLEFT, which relates to the question why a person left a previous job.

The MEPS used dependent interviewing in Rounds 3, 4, and 5 for Panel 10 and in Rounds 2 and 3 for Panel 11 (see section RJ in the employment section of the questionnaire). In these rounds, the MEPS asked persons who held current main and current miscellaneous jobs at the previous round interview date whether they were still working at these jobs. For other job types (former, last, or retirement) reported in the previous round, MEPS does not ask any follow-up questions. These jobs, by definition, are no longer held by the person and therefore are not included on the file except in the round they are first reported.

With dependent interviewing, if a person still held a Current Main Job from the previous round, the MEPS asked whether the job was still the main job. Most persons reported that they still worked at the same job and it was still their main job. If, in a subsequent interview, a job was no longer held, it was designated as a former job for that follow-up round. It is also possible, although unusual, for a job to change from main or miscellaneous (or vice versa) in a round subsequent to the initial report.

If job status remained the same for a continuing job (either main or miscellaneous), the MEPS asked only a subset of the employment questions as a review. Because the MEPS asked only this subset of questions if job status for a person did not change in later rounds, many job-level variables on the subsequent round’s job records are coded as inapplicable (-1); the complete information is on the record for the job in the first round in which it was reported. Thus, it is important to determine whether a job in a subsequent round continues from the previous round when working with the job records. In rounds where this applies, the variables STILLAT (for jobs that were current main in the previous round) and STILLWRK (for jobs that were current miscellaneous in the previous round) indicate whether a person still holds the job at the subsequent round interview date. The variable SUBTYPE on the subsequent round record indicates whether the job is main or miscellaneous in that subsequent round. Note that if a Panel 10 job included in this 2006 file is continued from a Round 1 or 2 job, much of the information will be contained in the 2005 MEPS Jobs file (HC-091). Use that file to obtain the desired job characteristics. Appendix 1 provides a sample SAS program showing how to do this.

Any new job reported in a round following the initial interview is collected the same way as in the first interview round.

Variables that relate only to the review of a job reported in a previous round (Y_CHANGE, MAIN_JOB, OFFTAKEI, NOWTAKEI, WHY_LEFT, STILLAT, STILLWRK, DIFFWAGE, WHY_DIFF, WORKSTAT, ESTBTHRU, INSESTB, NELIGINS) were not asked in Round 1, and these variables are coded as inapplicable (-1) on a Jobs record for the round in which the job is initially reported.

Unlike the situation explained above for most variables on the file, for certain variables a value other than inapplicable (-1) does not necessarily mean that a job is newly reported. There are two distinct situations in which this special treatment is used, due to internal processing needs.

In the first situation, questions related to the affected variables are skipped over as inapplicable (-1) during the interview in rounds subsequent to the one in which the job was initially reported, but have their originally reported response carried forward from round to round. This group includes the following 15 variables: EMPLINS, HRSPRWK, HRS35WK, JOBTYPE, JSTRTY, JSTRTM, JSTRTD, MORELOC, NUMEMPS, OFFRDINS, PROVDINS, TYPEEMPL, JOBHASHI, HRSALBAS, and RETIRJOB.

In the other situation, there are certain questions that are asked during the review of a job in rounds following the round in which the job was initially reported. If there is no change based on the review, the value for the affected variable is copied forward from the previous round. If there is a change, the variable is updated to reflect the new information. These five variables are: JSTOPY, NOWTAKEI, OFFTAKEI, SUBTYPE, and TOTLEMP.

Variables related to earnings (such as HRLYWAGE, GROSSPAY, SALARIED) are treated similarly to the five variables just discussed. In the review section, the MEPS attempted to obtain information regarding changes in wages for the same job from round to round. If there were no wage changes (indicated by the DIFFWAGE variable), then the most recent round’s information was carried forward. If changes were recorded, then the relevant variables were updated. For every new job reported for a person, the MEPS attempted to obtain current wage information.

For reasons of confidentiality, earnings variables on the file were top-coded. The earnings variables include HRLYWAGE, BONSAMT, COMMAMT, TIPSAMT, DAYWAGE, WKLYAMT, GROSSPAY, MAKEAMT, and OTHRWAGE. A value of ‘-10’ for one of these variables on a record indicates that the variable had a positive value and that the hourly rate for that earnings variable for the record was greater than or equal to $72.12. As of the Full-Year 2005 Jobs File, the process by which this value is derived was modified to incorporate the wage top-code process for the Full-Year 2005 Use File. The purpose of this change in top-coding procedures is to ensure confidentiality for each person across files. The Full-Year 2006 Jobs File continues to reflect this revised process.

Beginning with the 2004 Use File process, top coding was changed to consider updated wages in any round – that is, in addition to using wages from the first report of a Current Main Job, he updated wages from that job reported in any subsequent round are also included in deriving the top-code value. On the Use File, any person who has a wage in any round that is greater than or equal to the top-code value will have all wages top-coded, regardless of round. And any person whose wages are top-coded on the Full-Year 2006 Use File has all wages on all jobs top-coded in the Jobs File.

Moreover, because other jobs where wages are reported are included in the Jobs File but not summarized in the Full-Year 2006 Use file (i.e. newly reported former main jobs and current/former miscellaneous jobs), and these wages may exceed the current year top-code value, wages for these jobs and all jobs belonging to the same jobholder are top-coded on the Full-Year 2006 Jobs File. In turn, the wages of these persons are top-coded in the Full-Year 2006 Use File as well.

Note too that there are some jobs where respondents indicate that a supplemental wage, such as a commission, tip, or bonus, is greater than or equal to the wage top code value, but, at that same job, base wage such as the annual salary is not. For these cases, only the tips, commissions, or bonus amounts were top coded on the job where they are greater than or equal to the wage top code value. All other wage amounts on all jobs for these persons were left as reported.

For some persons in Panel 10, whose wages were imputed in Round 1 or Round 2 and copied forward into the FY 2006 USE PUF wage variable HRWG31X, the updated Round 3 wage as reported in the FY 2006 JOBS File may meet or exceed the wage top code value. For these cases, the main wage at the job is set to ‘-9’ and all other wage responses remain as reported.

Some wage information was logically edited for consistency. Edits were performed under three circumstances:

• in cases where a respondent updated a wage, indicating as the reason for the change that the amount reported in a previous round was in error, and then provided the corrected amount for the previous round
• in some cases where wages reported as less than $1.00 per hour are updated in a subsequent round to greater than $1.00, and the wage increased by a factor of 10 or 100 (for example, if a Round 4 wage is updated to $20.00, the Round 3 wage of $0.20 could logically be updated to $20.00); in some of these cases, additional comments may have also indicated an error
• in some cases where wages changed substantially from round to round and a keying error was evident (for example, ‘the number of hours on which the salary is based’ is updated from ‘40’ to ‘4’; the ‘4’ could logically be updated to ‘40’)

In all cases that result in an edit, a complete review of wage and employment history is performed; in some cases, comparisons are made to employment at similar establishments within the MEPS as well as to data reported and summarized by the Bureau of Labor Statistics.

To calculate the hourly rate for earnings types not reported on an hourly basis, the number of hours per week worked and in some cases the number of weeks worked were used in conjunction with the various amounts. These hours and weeks are included on the file along with the reported earnings amounts, but not the calculated hourly rates. (Earnings variables were not reconciled with income data collected elsewhere in the MEPS.)

Also for confidentiality reasons, the establishment size variables NUMEMPS (establishment size for jobs held by wage earners) and TOTLEMP (establishment size for self-employed jobs) were top-coded as ‘-10’ for establishment sizes greater than or equal to 11,000 employees.

It is important to note that the establishment size variable for the self-employed is TOTLEMP, while the establishment size for wage earners can be found in NUMEMPS and ESTMATE1. The variable ESTMATE1 is derived from a question that allowed wage earners who did not know the actual establishment size (NUMEMPS) to choose from a number of size ranges.

Two variables on the file pertain to the temporary and seasonal nature of a person’s main or miscellaneous job. The variable TEMPJOB indicates whether a main or miscellaneous job is temporary (e.g., is a current main job for a limited amount of time or until the completion of a project). The variable SESNLJOB indicates either that a main or miscellaneous job is available only during certain times of the year or that the individual is working throughout the entire year at that job. Teachers and other school personnel who work only during the school year are considered to work year round. In the collection instrument, the questions related to temporary and seasonal job characteristics are asked both when a current job is initially reported as well as during a review of that job. If a respondent reports during a review of a job that the job has ended, the questions are still asked. These questions are not asked of newly reported former miscellaneous jobs, last job outside of reference period, and retirement jobs.

Questions about employment-related health insurance are asked both when any type of job is newly reported and when any continuing job is reviewed. For main jobs, either newly reported or changing from miscellaneous, the variable that indicates whether insurance is held through that establishment is EMPLINS. For all non-main jobs, the variable JOBHASHI indicates whether insurance is held through that establishment.

For a newly reported job, depending on whether employment-related insurance is held or not, there may be follow-up information gathered which is contained in the following variables:

• OFFRDINS which notes if insurance was not held whether it was offered;
• DIFFPLNS which notes if a choice of plans is available where insurance is either offered or held;
• ANYINS which notes if insurance coverage is available to any other employees at the establishment in cases where the jobholder does not hold and is not offered coverage; and
• ELIGINSR which notes why the jobholder is not eligible for coverage in cases where other employees at the establishment are offered coverage.

For a continuing job, when no insurance was held in the round in which the job was first reported but insurance was offered, OFFTAKEI is asked to determine if it is now held in this round. If not, there is no follow-up regarding insurance coverage through that job. When insurance was not previously held nor offered, the follow-up questions in the RJ section relate to the following variables:

• NOWTAKEI indicates if insurance is now held through the establishment. If not, the jobholder is asked if health insurance was offered (ESTBTHRU).
• If insurance was not offered, follow-up questions are asked regarding insurance availability to any employees and why the jobholder is not eligible for that coverage as noted in the variables INSESTB and NELIGINS.
• If insurance was held for a portion of the previous round or the respondent disavows coverage in the Health Insurance section that was previously indicated in the Employment section of the interview, only NOWTAKEI is asked in subsequent rounds.

Due to many skip patterns, it is recommended that users of the Jobs file become familiar with the Employment section in the MEPS questionnaire. To aid users, a crosswalk between variables and MEPS questionnaire numbers is provided in this release. The following examples of variables involved in skip patterns are presented to be illustrative; these examples do not represent the full range of variables affected by questionnaire skip patterns.

In one example of a skip pattern, the MEPS did not obtain job-related benefits such as vacation, sick leave and pension information for self-employed jobs, so those variables are coded as inapplicable (-1) for those types of jobs. Nor did the MEPS attempt to obtain wage, salary, and information regarding whether the job was in the private sector, federal or local government (TYPEEMPL) for the self-employed. So again, due to the skip pattern, TYPEEMPL is coded as inapplicable (-1) for self-employed jobs.

Conversely, the questions relating to business organization type (BUSINC, PROPRIET) were asked only of the self-employed, so the skip pattern results in those variables being coded inapplicable (-1) for jobs performed by wage earners.

Industry and occupation codes were assigned by professional coders at the Census Bureau based on verbatim descriptions provided by respondents during the survey interview. The codes are determined at a detailed 4-digit level and then collapsed into broader groups on the file to ensure the confidentiality of the records. INDCODEX contains industry information and OCCCODEX contains occupation information.

As of the Full Year 2002 MEPS deliveries, the Census Bureau began using an updated coding scheme for both industry and occupation. Therefore, the industry and occupation variables for pre-2002 files are not comparable to those for 2002 and later files. See the 2002 Jobs File (HC-063) for crosswalks of the 2002 (new) and 1990 (old) detailed-to-condensed Census industry and occupation codes.

This 2006 Jobs file does not include any weights necessary to extrapolate this data to the U.S. population. To make person-level estimates, link to any of the 2006 MEPS files and use the person-level weight for the appropriate panel. The link should be made through the variable DUPERSID. Note that not all persons in the MEPS have positive weights and job records; only those persons who have either a positive person-level or family-level weight in the 2006 Full-Year Person-Level file are included in the 2006 Jobs file.

Return To Table Of Contents

For each variable on the 2006 Jobs file, an unweighted frequency is provided in the accompanying codebook file.

Return To Table Of Contents

The following reserved code values are used:

Return To Table Of Contents

This codebook describes an ASCII dataset (with related SAS and SPSS programming statements and data user information), although the data are also provided in a SAS transport file. The file contains 87 variables and has a logical record length of 254 with an additional 2-byte carriage return/line feed at the end of each record. The following codebook items are provided for each variable:

Return To Table Of Contents

In general, variable names reflect the content of the variable, with an 8-character limitation. Variables contained on this file were derived from the questionnaire itself or from the CAPI. The source of each variable is identified in Section D. Variable-Source Crosswalk. Sources for each variable are indicated in one of two ways:

Return To Table Of Contents

To facilitate analysis of subpopulations and/or low prevalence events, it may be desirable to pool together more than one year of data to yield sample sizes large enough to generate reliable estimates.  For more details on pooling MEPS data files see www.meps.ahrq.gov/data_stats/download_data_files_detail.jsp?cboPufNumber=HC-036.

Starting in Panel 9, values for DUPERSID from previous panels will occasionally be re-used. Therefore, it is necessary to use the panel variable (PANEL) in combination with DUPERSID to ensure unique person-level identifiers across panels. Creating unique records in this manner is advised when pooling MEPS data across multiple annual files that have one or more identical values for DUPERSID.

Return To Table Of Contents

Panel-specific files containing estimation variables to facilitate longitudinal analysis are available for downloading in the data section of the MEPS Web site.

Return To Table Of Contents

3.2 Using MEPS Data for Trend Analysis

MEPS began in 1996 and the utility of the survey for analyzing health care trends expands with each additional year of data.  However, it is important to consider a variety of factors when examining trends over time using MEPS. Statistical significance tests should be conducted to assess the likelihood that observed trends are not attributable to sampling variation. The length of time being analyzed should also be considered. In particular, large shifts in survey estimates over short periods of time (e.g. from one year to the next) that are statistically significant should be interpreted with caution, unless they are attributable to known factors such as changes in public policy, economic conditions, or MEPS survey methodology. Looking at changes over longer periods of time can provide a more complete picture of underlying trends. Analysts of MEPS data may wish to consider using techniques to evaluate, smooth, or stabilize estimates of trends<.  Such techniques include comparing pooled time periods (e.g. 1996-97 versus 2005-06), working with moving averages, or using modeling techniques with several consecutive years of MEPS data to test the fit of specified patterns over time.  Finally, researchers should be aware of the impact of multiple comparisons on Type I error (i.e., the chance of declaring an observed difference to be statistically significant when there is no difference in the population parameters). Performing numerous statistical significance tests increases the likelihood of a Type I error.

Return To Table Of Contents

Return To Table Of Contents

Return To Table Of Contents

Appendix 1: Sample SAS Program (open in a separate file)

Return To Table Of Contents