Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 104 - Survival Analysis in Causal Inference Studies
Type: Invited
Date/Time: Monday, August 3, 2020 : 1:00 PM to 2:50 PM
Sponsor: Lifetime Data Science Section
Abstract #309209
Title: A General Approach of Assessing the Bias of 2 Stage IV Models for Survival Outcomes
Author(s): Fei Wan*
Companies: Washington University in St. Louis
Keywords: instrumental variable; survival outcome; unmeasured confounding; 2SRI; omitted variable bias; proportional hazards model
Abstract:

Observational studies are commonly used to evaluate the relative effectiveness of different treatment options. To address unmeasured confounding, instrumental variable (IV) methods have become increasingly popular. Specifically, two-stage residual inclusion (2SRI) has become a common analytic tool in studies of cancer therapies where the outcome of interest is overall or cancer-specific survival. However, despite its popularity, a compelling theoretical rationale has not been postulated nor have the limitations underlying the use of 2SRI in the context of survival outcomes been carefully laid out. In this study we first provide a brief description of the concept of instrumental variables and their underlying assumptions, and describe the 2SRI approach. We show that the previous conclusion on the consistency of 2SRI holds under the following conditions: (1) when the null hypothesis is true; (2) when the outcome model is collapsible. Given a perfect instrumental variable, extension of 2SRI to proportional hazards model can generally result in biased estimates of treatment effect. We present a simple approach of assessing the bias of 2SRI as an omitted- variable-bias problem.


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

Back to the full JSM 2020 program