An Example of a Longitudinal Analysis Using the Medical Expenditure Panel Survey (MEPS)

• Activity Number: 181
• Type: Contributed
• Date/Time: Tuesday, August 13, 2002 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods*
• Author(s): Janet Greenblatt*+
• Affiliation(s): Agency for Healthcare Research and Quality
• Keywords: MEPS ; NHIS ; longitudinal ; survey ; survey weights

Abstract

The Medical Expenditure Panel Survey (MEPS) is an ongoing panel survey designed to produce annual estimates of the health care utilization, expenditures, sources of payment, and insurance coverage of the U.S. civilian noninstitutionalized population. The MEPS sample design is a stratified multistage area probability design with disproportionate sampling to facilitate the selection of an oversample of persons with characteristics of particular policy interest. The MEPS households are drawn from completed interviews in the prior year of the National Health Interview Survey (NHIS). Each MEPS panel can be linked to the previous year's NHIS. A new panel is selected annually and data are collected from each panel five times over a thirty-month period to obtain expenditure data for two consecutive years. Longitudinal files have been constructed two of the MEPS panels; one from the 1996 panel and one from the 1997 panel. The method by which the longitudinal files and weights were constructed will be discussed. An example will be given, using SAS and SUDAAN, for analyzing the difference between medical expenditures for year one and for year two of the 1996 panel.