Statistical Analyses of Correlated Medical Cost Data

• Activity Number: 230
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Lei Liu*+
• Companies: University of Virginia
• Keywords: mixed models ; random effects ; zero-inflated ; health econometrics

Abstract

The recently rekindled debate on health care reform in the U.S. and interest in how to pay for an expanded national program of care provides motivation to better model medical cost data. In practice, medical costs could be correlated, e.g., longitudinal medical costs, where costs accumulated within different time intervals are correlated for the same subject. In this talk, we will present new statistical model to analyze the correlated medical costs data. In particular, we will show how to extend the traditional medical cost models (two-part models and sample selection models, e.g., Tobit model), to the correlated data setting. We will compare the performance of these models through real data analysis.