Online Program Home
  My Program

Abstract Details

Activity Number: 184 - SPEED: Variable Selection and Networks
Type: Contributed
Date/Time: Monday, July 31, 2017 : 11:35 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #325246
Title: Bayesian Adjustment for Confounding When Estimating Average Causal Effects for Time-To-Event Outcomes
Author(s): Li Xu* and Arnold Stromberg and Chi Wang
Companies: and Department of Statistics, University of Kentucky and Cancer Biostatistics, University of Kentucky
Keywords: Bayesian Adjustment for Confounding ; causal inference ; variable selection ; Bayesian model averaging
Abstract:

Bayesian Adjustment for Confounding when Estimating Average Causal Effects for Time-to-event Outcomes

Li Xu, Arnold Stromberg, Chi Wang

The Bayesian adjustment for confounding (BAC) is a Bayesian model averaging method to select and adjust for confounding factors when evaluating the average causal effect of an exposure on a certain outcome. We extend the BAC method to time-to-event outcomes. Specifically, the posterior distribution of the exposure effect on a time-to-event outcome is calculated as a weighted average of posterior distributions from a number of candidate proportional hazards models, weighing each model by its ability to adjust for confounding factors. The Bayesian Information Criterion based on the partial likelihood is used to compare different models and approximate the Bayes factor. The posterior sample of the exposure effect is obtained using OPENBUGS. Performance of our method is assessed using simulation studies.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association