|
Abstract:
|
It has been increasingly common to analyze simultaneously repeated measures and survival. In this talk we propose a joint model when repeated measures are semi-continuous, characterized by the presence of a large portion of zero values, as well as right skewness of positive values, e.g., monthly medical costs, car insurance annual claims, etc. A random effects two-part model is used to model respectively the odds of being positive and the actual amount of positive values. The random effects from the two-part model are then incorporated in the hazard of the failure time to form the joint model. Estimation is proceeded by Gaussian quadrature techniques conveniently implemented in SAS Proc NLMIXED. Our model is applied to monthly medical costs of 1455 chronic heart failure patients from the clinical data repository (CDR) at the University of Virginia.
|
