This study examines the effect of multiple prior years of health expenditures on the probability of enrollment in a Medicare HMO. Beneficiaries may require more than one year of prior expenditure data to form a reliable estimate of future expenditures if health expenditures have a significant transitory component. We used a logit model to estimate the influence of 1991-1993 Part A expenditures and demographic data on the choice of health plans in 1994. The results indicate that beneficiaries use multiple years of expenditures in their choice of health plan and the effect of prior spending declined with time.
|Original language||English (US)|
|Number of pages||15|
|Journal||International journal of health care finance and economics|
|State||Published - Sep 2004|
Bibliographical noteFunding Information:
We acknowledge helpful comments from Gerald Riley, our project officer, and two anonymous reviewers. The authors are responsible for any remaining errors. The opinions expressed are those of the authors and do not necessarily reflect the views of the Centers for Medicare and Medicaid Studies, the Veterans Administration, the University of Washington or the University of Minnesota. This research was supported by CMS (formerly HCFA) 99-0074-E01.