|
Activity Number:
|
674
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 4, 2016 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
ENAR
|
|
Abstract #318140
|
|
|
Title:
|
Cox Model Asymptotic Distributional Theory of Weighted Estimation for Nested Case-Control Design
|
|
Author(s):
|
Bin Nan* and Ross Prentics and Tianxi Cai
|
|
Companies:
|
University of Michigan and Fred Hutchinson Cancer Research Center and Harvard
|
|
Keywords:
|
Empirical process ;
Inverse probability weighting ;
Sampling with replacement ;
Z-estimation theory
|
|
Abstract:
|
Existing literature shows the improved efficiency of the inverse probability weighted approach compared with the matched set conditional likelihood method for the nested case-control study via numerical examples, but the inverse probability weighted estimator lacks a rigorous asymptotic theory. We consider the design where time-matched controls are sampled with replacement and provide a proof of the asymptotic theory of the weighted estimator using modern empirical process theory.
|
Authors who are presenting talks have a * after their name.
