|
Activity Number:
|
357
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
General Methodology
|
| Abstract - #301442 |
|
Title:
|
Confidence Sets for Semiparametric Models Using MCMC
|
|
Author(s):
|
John Dixon*+ and Michael Kosorok
|
|
Affiliation(s):
|
University of Wisconsin, Madison and University of Wisconsin, Madison
|
|
Address:
|
, Madison, Wisconsin, ,
|
|
Keywords:
|
semiparametric inference ; survival analysis ; confidence sets ; empirical processes ; markov chain monte carlo ; bootstrap
|
|
Abstract:
|
We consider confidence sets for a class of semiparametric models, which includes frailty regression models arising in survival analysis. We propose a method of obtaining random draws for the parametric and nonparametric components of such a model, that is a combination of the Markov Chain Monte Carlo and Bootstrap methods. When centered about the maximum likelihood estimates, these draws have a distribution conditional on the data that is asymptotically equivalent to the sampling distribution of the MLEs, allowing the construction of confidence sets. The procedure has the advantage over the unmodified bootstrap in that one does not need to maximize the bootstrap likelihood. We illustrate the procedure with a data set.
|
- 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 2002 program |
