Predicting Medical Expenditures Using Survey Data

• Activity Number: 77
• Type: Topic Contributed
• Date/Time: Monday, August 9, 2004 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Joel W. Cohen*+
• Companies: Agency for Healthcare Research and Quality
• Keywords: medical expenditures ; predicting expenditures ; persistence of expenditures ; Medical Expenditure Panel Survey

Abstract

Research on the distribution of health care expenditures among the U.S. population has shown that a small proportion of individuals accounts for a disproportionate share of total expenses. Work by Berk and Monheit using the 1977 National Medical Care Expenditure Survey (NMCES), 1987 National Medical Expenditure Survey (NMES) and the 1996 Medical Expenditure Panel Survey (MEPS) indicates that the top 1% of that distribution accounts for more than one-quarter of all expenses, and the top 5% accounts for more than half. Additional work on the persistence of high expenditures, however, suggests that in general being in the top of the expenditure distribution is not something that is highly persistent over time. Although expenditures in one year are correlated with expenditures in the next, there are a number of other factors that determine individuals' levels of spending, including his or her health conditions. The ability to accurately predict expenditures is critical for both ensuring adequate coverage of high expenditure individuals in survey samples, and for determining efficient treatment regimens for these individuals in both private and public health plans.