Medical Expenditure Panel Survey (MEPS) for Dementia Researchers, 2015-2019
Principal Investigator(s): View help for Principal Investigator(s) Julie Bynum, University of Michigan
Version: View help for Version V1
| Name | File Type | Size | Last Modified |
|---|---|---|---|
| Code | 11/11/2021 03:23:PM | ||
| Data | 11/11/2021 03:20:PM | ||
| Data-Dictionaries | 11/11/2021 03:19:PM | ||
|
|
text/plain | 2.7 KB | 11/11/2021 10:24:AM |
Project Citation:
Bynum, Julie. Medical Expenditure Panel Survey (MEPS) for Dementia Researchers, 2015-2019. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2021-11-30. https://doi.org/10.3886/E154381V1
Project Description
Summary:
View help for Summary
This series of code and corresponding data files
are intended for use in cognitive decline and Alzheimer’s disease and related
dementias (ADRD) research. The files include five datasets derived from the 2015-2019
Medical Expenditure Panel Survey (MEPS). MEPS provides users with detailed
information on the cost and use of health care and health insurance coverage in
the U.S., surveying families and individuals, their medical providers, and
employers.
The provided datasets include sociodemographic information on respondents’ census region, age, sex, marital status, race, and education level, cognition questions, and health care expenditures and use from the Household Component Full-Year Consolidated Data File. These data were merged onto the Medical Components File identifying respondents with ADRD or other cognitive impairments using truncated ICD-9/ICD-10 codes. Brief and detailed summaries of the variables available in these datasets along with more detailed descriptions of performed calculations can be found in the provided data dictionaries. SAS, Stata, and CSV file formats are provided as are the full coding scripts used in both SAS and Stata.
The provided datasets include sociodemographic information on respondents’ census region, age, sex, marital status, race, and education level, cognition questions, and health care expenditures and use from the Household Component Full-Year Consolidated Data File. These data were merged onto the Medical Components File identifying respondents with ADRD or other cognitive impairments using truncated ICD-9/ICD-10 codes. Brief and detailed summaries of the variables available in these datasets along with more detailed descriptions of performed calculations can be found in the provided data dictionaries. SAS, Stata, and CSV file formats are provided as are the full coding scripts used in both SAS and Stata.
Funding Sources:
View help for Funding Sources
United States Department of Health and Human Services. National Institutes of Health. National Institute on Aging (AG066582)
Scope of Project
Subject Terms:
View help for Subject Terms
aging;
cognition;
cognitive impairment;
Dementia;
Alzheimers disease;
ADRD;
cognitive functioning;
memory;
CAPRA
Geographic Coverage:
View help for Geographic Coverage
U.S.A.
Time Period(s):
View help for Time Period(s)
2015 – 2019
Universe:
View help for Universe
Sample of families and individuals in selected
communities across the U.S., drawn from a nationally representative subsample
of households that participated in the prior year’s National Health Interview
Survey (NHIS). NHIS samples from noninstitutionalized U.S. Adults and families.
IMPORTANT NOTE: NHIS does not sample from persons in long-term care institutions (e.g., nursing homes)
IMPORTANT NOTE: NHIS does not sample from persons in long-term care institutions (e.g., nursing homes)
Data Type(s):
View help for Data Type(s)
program source code;
survey data
Collection Notes:
View help for Collection Notes
Users of this resource should be familiar with
complex survey design and appropriately apply the sample weights, strata, and
primary sampling units for any analyses. perwtf should be used for person-level
analyses; famwtf should be used for family-level analyses. Cognition related
questions were only asked of adults 18-years and older. Missingness in the claims variables (e.g., adrdci) indicates that a person was not represented in the medical components file.
MEPS uses a panel design where respondents answer 5 series of questions across two calendar years. If users wish to combine multiple years of data, they should be aware that some respondents may appear more than once.
The list of truncated ICD-9 and ICD-10 codes are below.
MEPS uses a panel design where respondents answer 5 series of questions across two calendar years. If users wish to combine multiple years of data, they should be aware that some respondents may appear more than once.
The list of truncated ICD-9 and ICD-10 codes are below.
- ICD-9 (2015 only): 290, 294, 331, 797
- ICD-10: F01, F02, F03, F04, G30, G31, R41
Methodology
Response Rate:
View help for Response Rate
See MEPS website
Sampling:
View help for Sampling
Complex survey data with a stratified, clustered
sampling design
Data Source:
View help for Data Source
Medical
Expenditure Panel Survey (MEPS) from the Agency for Healthcare Research and
Quality (AHRQ)
Collection Mode(s):
View help for Collection Mode(s)
computer-assisted personal interview (CAPI);
other
Weights:
View help for Weights
perwtf should be used for person-level analyses; famwtf should be used for family-level analyses.
Unit(s) of Observation:
View help for Unit(s) of Observation
Person
Geographic Unit:
View help for Geographic Unit
U.S. Census Region
Related Publications
Published Versions
Report a Problem
Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.
This material is distributed exactly as received from the data depositor. As of April 2026, depositors are required to submit study materials in accessible formats. ICPSR has not reviewed, checked, or processed this material. For additional information about the study, please contact the investigator(s) directly. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR's Accessibility Center.