|
Activity Number:
|
96
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #309123 |
|
Title:
|
Bayesian Variable Selection in Proportional Hazards Models with Frailties
|
|
Author(s):
|
Zhen Chen*+
|
|
Companies:
|
University of Pennsylvania
|
|
Address:
|
423 Guardian Drive, Philadelphia, PA, 19104,
|
|
Keywords:
|
Proportional hazards ; Frailty ; Variable selection ; Cluster ; MCMC ; cancer
|
|
Abstract:
|
We apply a Bayesian approach to define prior distributions for frailty variances in a PH model consisting of mixtures of point masses at zero and inverse-gamma densities. This prior allocates probability to each of the models including the overall null hypothesis of homogeneity. Using a counting process formulation, the conditional posterior distributions of the frailties and proportional hazards regression coefficients have simple forms. Posterior computation proceeds via a data augmentation Gibbs sampling algorithm, a single run of which can be used to obtain model-averaged estimates of the population parameters and posterior model probabilities for testing hypotheses about the heterogeneity structure. The methods are illustrated using data from a lung cancer trial.
|
