Refining the Prediction Models of Low Income Status and Future Medical Expenditures In the Medical Expenditure Panel Survey

• Activity Number: 345
• Type: Topic Contributed
• Date/Time: Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
• Sponsor: Section on Health Policy Statistics*
• Author(s): Lap-Ming Wun*+ and Steven Cohen and John Moeller
• Affiliation(s): Agency for Health Care Policy and Research and Agency for Healthcare Research and Quality and Agency for Healthcare Research and Quality
• Keywords: logistic regression ; predicted probability ; low income ; high expenditure

Abstract

The Medical Expenditure Panel Survey (MEPS) is sponsored by the Agency for Healthcare Research and Quality (AHRQ). It is conducted to provide nationally representative estimates of health care use, expenditures, sources of payment, and insurance coverage for the U.S. civilian noninstitutionalized population. It comprises three component surveys with the Household Component (HC) as the core survey. For selected years, the sample of the MEPS HC includes an oversample of several targeted subpopulations which include individuals with low income and individuals ages 18-64 who are likely to incur high medical expenditures. However, the status of an individual's income and medical expenditure is not known at the time the sample is drawn. These characteristics have to be predicted. Predictive models for these characteristics were established using the data from 1987 National Medical Expenditure Survey (NMES), the predecessor of MEPS, and a 1986 screener survey. This report presents the procedure and results of updating these models using the latest available data from the 1997 National Health Interview Survey (NHIS) and from the 1998 MEPS.