|
Activity Number:
|
518
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #303442 |
|
Title:
|
Causal Estimation for the Proportional Hazard Model with Prevalent Sampling
|
|
Author(s):
|
Yu-Jen Cheng*+ and Mei-Cheng Wang
|
|
Companies:
|
Johns Hopkins University and Johns Hopkins Bloomberg School of Public Health
|
|
Address:
|
615 N. Wolfe Street E3035, Baltimore, MD, 21205,
|
|
Keywords:
|
Measurement Error ; Smoothing ; Survival analysis
|
|
Abstract:
|
The objective of this article is to make inference on the marginal causal survival function and the propensity score in prevalent sampling. The problem is especially complex because outcome ("potential outcomes"), as well as covariates, are partially observed. The missingness comes from two different sources: One is due to the hypothetic potential outcome framework; the other is because of the prevalent sampling scheme. The Cox model is considered in this article. Making causal inference without adjusting for both sources of the missingness will lead to a bias result. We propose an inverse weighting approach to estimate average causal survival function and developed a method to correct the propensity score. Furthermore, we modified the stratification and regression adjustment approach based on corrected propensity score. Large sample properties of our estimators based on empirical processes are derived in this article. Our methodology was motivated by and applied to Surveillance, Epidemiology, and End Results (SEER)-Medicare data for women diagnosed with breast cancer.
|
