Online Program Home
My Program

Abstract Details

Activity Number: 479 - Survival Analysis II
Type: Contributed
Date/Time: Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #329769 Presentation
Title: Cox Regression Model Under Dependent Truncation with Applications to Studies of Neurodegenerative Diseases
Author(s): Lior Rennert* and Sharon X Xie
Companies: Clemson University and University of Pennsylvania
Keywords: Alzheimer's disease; Cox regression model; Observational studies; Survival; Selection bias; Truncation

Existing methods to adjust for both left and right truncation (i.e. double truncation) in the Cox regression model all require independence between the survival times and truncation times, which may not be a reasonable assumption in practice. When left, right, or double truncation is not accounted for, or the assumption of independence is violated, existing methods yield biased regression coefficient estimators. We propose an expectation-maximization algorithm to relax the independence assumption in the Cox regression model under left, right, or double truncation. The resulting regression coefficient estimators are consistent and asymptotically normal. We demonstrate through extensive simulations that the proposed estimators have little bias, and are almost as efficient, or more efficient, than existing estimators under left, right, or double truncation, regardless of the dependence structure. Studies of neurodegenerative diseases which rely on autopsy-confirmed diagnoses are inherently subject to double truncation. We implement our approach to detect predictors of survival in subjects with autopsy-confirmed Alzheimer's disease.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program