|
Activity Number:
|
396
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #305159 |
|
Title:
|
Semiparametric Models with Data Missing by Design and Inverse Probability Weighted Empirical Processes: Partial Results and Open Problems
|
|
Author(s):
|
Jon A. Wellner*+
|
|
Companies:
|
University of Washington
|
|
Address:
|
Department of Statistics, Box 354322, Seattle, WA, 98195-4322,
|
|
Keywords:
|
Horvitz-Thompson processes ; exchangeable bootstrap ; missing data ; sampling without replacement
|
|
Abstract:
|
Horovitz-Thompson or inverse probability weighted (IPW) versions of likelihood equations provide one simple method of estimation for two-phase stratified sampling designs. In this talk, I will discuss results for the basic Horovitz-Thompson empirical processes, which allow study of the asymptotic behavior of estimators for semiparametric models with nuisance parameters---which can be estimated at rate square-root n. The results are based on theorems for exchangeably weighted bootstrap methods obtained in the early 1990s. This talk will complement a related talk by Norman Brewlow on different aspects of the same problem.
|
- 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 |
