On the Correlated Gamma Frailty Model for Bivariate Current Status Data

• Activity Number: 467
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Niel Hens*+ and Andreas Wienke
• Companies: Hasselt University and University Halle-Wittenberg
• Keywords: Correlated gamma frailty ; Bivariate current status data ; Heterogeneity

Abstract

Frailty models are often used to study the individual heterogeneity in multivariate survival analysis. Whereas the shared frailty model is widely applied, the correlated frailty model has gained attention because it elevates the restriction of unobserved factors to act similar within clusters. Estimating frailty models is not straightforward due to various types of censoring. In this abstract focus is on Type II interval censored data commonly known as current status data for which we study the behavior of the correlated gamma frailty model. We show that the correlated frailty model for bivariate current status data is identifiable when using a parametric baseline hazard but that misspecification of the frailty component or the baseline hazard can lead to biased estimates. We illustrate these results on multisera data of hepatitis A and B.