Bivariate Copula Random-Effects Model for Loss and Cost

• Activity Number: 679
• Type: Topic Contributed
• Date/Time: Thursday, August 8, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Xiaoqin Tang*+ and Zhehui Luo and Joseph Gardiner
• Companies: Geisinger Health System and Michigan State University and Michigan State University
• Keywords: copula families ; random effects ; joint model ; LOS ; costs

Abstract

Copula models and random effect models are becoming increasingly popular for modeling dependencies or correlations between random variables. The range of their recent scientificapplications include such fields as economics, finance, insurance and survival analysis. The paper gives a brief overview of the principles of construction of such copula models from the Farlie-Gumbel-Morgenstern, Gaussian, and Archimedean families including Frank, Clayton, and Gumbel families. We develop a new flexible joint model for correlated measurement errors modeled by copulas and incorporate a cluster level random effect to account for individual and within-cluster correlations simultaneously. In an empirical application our proposed approach attempts to capture the various dependence structures of hospital length of stay and cost (symmetric or asymmetric) in the copula function, and takes advantage of the relative ease in specifying the marginal distributions and introduction of within-cluster correlation based on the cluster level random effects.