|
Activity Number:
|
422
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305946 |
|
Title:
|
Asymptotic Theory for the Proportional Hazards Model with Random Effects
|
|
Author(s):
|
Anthony C. Gamst and Michael Donohue*+ and Ronghui Xu
|
|
Companies:
|
University of California, San Diego and University of California, San Diego and University of California, San Diego
|
|
Address:
|
3855 Health Sciences Drive 0901, La Jolla, CA, 92093-0901,
|
|
Keywords:
|
correlated failure time data ; proportional hazards ; survival data
|
|
Abstract:
|
We will study the proportional hazards mixed effects model (PHMM) of Vaida and Xu (2000), which is a natural extension of the conventional proportional hazards model to handle clustered event time data. Maximum likelihood estimates under PHMM have been widely utilized without theoretical justification since being proposed. Under regularity and identifiability assumptions, we show consistency, asymptotic normality, and asymptotic efficiency of the maximum likelihood estimates of the model. The proof uses methods that Murphy (1994, 1995) applied to the frailty model, and Zeng, Lin, and Yin (2005) recently applied to the proportional odds mixed effects model.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |
