|
Activity Number:
|
426
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305428 |
|
Title:
|
A Positive Stable Frailty Model for Clustered Failure Time Data with Covariate Dependent Frailty
|
|
Author(s):
|
Dandan Liu and John D. Kalbfleisch*+ and Douglas E. Schaubel
|
|
Companies:
|
University of Michigan and University of Michigan
|
|
Address:
|
M4148 SPH II , Ann Arbor, MI, 48109,
|
|
Keywords:
|
Clustered failure Time ; Covariate dependent frailty ; Positive stable frailty ; Cox model
|
|
Abstract:
|
In this article, we propose a positive stable shared frailty Cox model for clustered failure time data where the frailty distribution varies with cluster level covariates. The proposed model accounts for covariate dependent intra-cluster correlation and permits both conditional and marginal inferences. We obtain marginal inference directly from the marginal model, then use a stratified Cox type pseudo-partial likelihood approach to estimate the regression coefficient for the frailty parameter. The proposed estimators are consistent and asymptotically normal and a consistent estimator of the covariance matrix is provided. Simulation studies show that the proposed estimation procedure is appropriate for a practical use with a realistic number of clusters. Finally, we apply the proposed method to kidney transplantation data from the Scientific Registry of Transplant Recipients.
|
