Data Products
The Center actively supports empirical research on aging by:
- facilitating the use of the Health and Retirement Study (HRS) and
Asset and Health Dynamics Among the Oldest Old (AHEAD) by providing
two data products, distributed as SAS or Stata files:
- the RAND HRS Data File, a particularly user-friendly file derived from all waves of the HRS and AHEAD, and
- the RAND-enhanced Fat Files (formerly known as Flat Files), which provide HRS/AHEAD raw variables in a single file per wave;
These data products may be used together or separately. Their use can expedite the preparation of analytic files from HRS/AHEAD data.
- maintaining a Contextual Data Library, which includes publicly available measures in a standard format, such as Consumer Price Indices (CPI), Social Security Cost of Living Adjustments, and poverty thresholds;
- supporting direct collection of survey data;
- providing Sas2stata, a Unix utility to convert SAS data sets into Stata format.
If you use or are considering use of HRS data, please see a brief overview of the RAND versions of HRS/AHEAD data and how they can help you get started using the HRS. We also provide help using RAND HRS Data Products.
Please cite the RAND HRS Data File as follows:
RAND HRS Data, Version H. Produced by the RAND Center for the Study of Aging, with funding from the National Institute on Aging and the Social Security Administration. Santa Monica, CA (February 2008 ).
You may want to include a footnote, the first time you refer to the file in the text of a paper, e.g.:
The RAND HRS Data file is an easy to use longitudinal data set based on the HRS data. It was developed at RAND with funding from the National Institute on Aging and the Social Security Administration.
You should also include the HRS citation (about half-way down the page).
The RAND HRS, Supported by NIA and SSA
With funds from the National Institute on Aging (NIA) and the Social Security Administration (SSA), the Center has developed data sets from the Health and Retirement Study (HRS) and Asset and Health Dynamics Among the Oldest Old (AHEAD) data which are collected by the Institute for Social Research (ISR) at University of Michigan.
Our most recent data development is the RAND HRS Data file, supported by NIA and SSA. This extraordinarily user-friendly file contains a wide-ranging set of derived variables based on the 1992, 1993, 1994, 1995, 1996, 1998, 2000, 2002, 2004 final release and 2006 early release data. It includes RAND imputations of wealth, income, and medical expenditures. All variables have been renamed using an intuitive and consistent naming scheme, and values labels have been assigned throughout. For example, self-reported health status in 1998 (HRS variable F1097) has been renamed R4SHLT (Respondent, Wave 4, Self-reported health), with value labels assigned (Excellent, Very good, Good, Fair, Poor, plus missing codes). The RAND HRS Data includes all five entry cohorts: HRS, AHEAD, Children of the Depression Age (CODA), War Babies (WB) and Early Baby Boomers (EBB).
A comprehensive codebook (1.8 Mb) provides descriptive statistics, raw HRS variables used, and derivation descriptions for each derived variable.
To access the data:
- You must first register with HRS, if you haven't already. Registration is free. You will receive a password from HRS within 24 hours, usually much sooner. When you receive your password, you can return here to continue.
- If you've already registered, login through the HRS Public File Download Area
- Once you have logged in, follow the "Datasets and Files" link, then the "RAND HRS Data File" link.
The file was originally developed for the Social Security Administration, which has also provided funds for its distribution through the Michigan Retirement Research Center (MRRC). It built on the NIA-sponsored enhanced HRS/AHEAD Fat Files with which it is easily merged.
Further development of the data set continues. The Center incorporates new releases of existing HRS data, corrects and improves variable derivations and documentation, and plans to continue to add new variables.
Enhanced HRS/AHEAD Fat Files (formerly known as Flat Files)
The Center has produced enhanced versions of "raw" HRS and AHEAD data files. Among the enhancements are:
- The HRS/AHEAD data are distributed in modules that are organized by questionnaire section. Some modules contain household-level variables, such as information on assets. We merged all modules into individual-level records. This eliminates the need to search through modules for particular variables and facilitates merging files across waves.
- The HRS/AHEAD collect certain individual-level information by asking one household member to answer about another. For example, the financial respondent provides earnings information for himself or herself and his or her spouse. We created new variables for "own" and "partner" information by re-assigning responses to the appropriate person.
There is a single Fat File for each year of HRS/AHEAD which contains most of the "raw" or original variables, merged to the respondent level. The Fat Files are available on request with preliminary documentation. [Note: No documentation is available for 2000, 2002, 2004 and 2006 at this time.] To request these files please provide your name, address (no PO Box), phone number and data format (SAS/Stata/SPSS) to RANDHRShelp@rand.org.
Available files include 1992, 1993, 1994, 1995, 1996, 1998, 2000, 2002, 2004 final release and 2006 early release data. These can easily be used with the current release of the RAND HRS. As part of the development of these data sets, the Center notes details of problems found in the data, and adds some generally useful variables. The RAND HRS Data file development begins with these enhanced "raw" files. For a more detailed view of how these files are enhanced, please see sample documentation for HRS 1992/1994, AHEAD 1993/1995, HRS 1996, and HRS 1998. These provide information on what has been added to raw HRS data in these files, but they are not codebooks or questionnaires. Codebooks and questionnaires may be found on the HRS web site. Note these versions of the documentation have not been updated for the most recent release of the Fat Files.
We urge you to regularly visit the HRS web site which provides a wealth of information about the data, including questionnaires, codebooks, background on study design, and data alerts.
Support for Data Collection
The Center has supported the following surveys and supplements:- Family Life Surveys in developing countries
- Panel Study of Income Dynamics (PSID) supplements, available from the PSID web site:
Send questions or comments about this webpage to RANDHRSHelp@rand.org
Top