|
Activity Number:
|
33
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #307488 |
|
Title:
|
Statistical Methods for Proportional Hazards Regression with Missing Covariates
|
|
Author(s):
|
Lihong Qi*+ and Ching-Yun Wang and Ross Prentice
|
|
Companies:
|
University of California, Davis and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center
|
|
Address:
|
Rowe Program in Human Genetics, Davis, CA, 95616,
|
|
Keywords:
|
case-cohort ; kernel smoother ; missing covariate data ; nested case-control ; nonparametric method ; weighted estimating equation
|
|
Abstract:
|
Missing covariate data are common in medical studies. In some situations, certain covariates are observed for all study subjects and other covariate data are collected only for a subset. Inconsistent and inefficient estimates can be generated by naively discarding subjects with incomplete data. In this talk, I will present both simple weighted and kernel-assisted fully augmented weighted estimators that use partially incomplete data nonparametrically. The resulting weighted estimators are more efficient than the simple weighted estimator with the inverse of true selection probability as weight. These weighted estimators allow the missing-data mechanism to depend on outcome variables and observed covariates, and they are applicable to various cohort sampling procedures, including case-cohort and nested case-control designs.
|
