Bayesian Multiply Robust Estimation for Causal Inference

• Activity Number: 56 - Causal Inference
• Type: Contributed
• Date/Time: Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Benjamin Gochanour* and Sixia Chen and Laura Beebe and David Haziza
• Companies: University of Oklahoma Health Sciences Center and University of Oklahoma Health Sciences Center and University of Oklahoma Health Sciences Center and University of Ottawa
• Keywords: Causal inference; Bayesian statistics; Multiply robust; Observational studies

Abstract

Observational studies have been used frequently in practice including epidemiology, medicine, economics, and other research fields. Causal inference has been regarded as one of the most effective tools for conducting statistical inference with observational studies without random treatment assignments. The validity of most existing causal inference procedures depends on the underlying outcome regression and/or propensity score modeling assumptions. In this paper, we propose some new Bayesian multiply robust estimation approaches for causal inference based on loss-likelihood bootstrap. The proposed methods enjoy multiply robustness property such that the estimators of treatment effect are consistent if at least one of the outcome regression models or propensity score models is correctly specified. Convenient statistical inference can be conducted by constructing Bayesian Posterior credible intervals. Simulation studies show the benefits of our proposed methods. We further apply our proposed methods by using 2017-2018 National Health Nutrition and Examination Survey (NHANES) data to examine the effect of exposure to perfluoroalkyl acids (PFAs) on kidney function.