Debiased Bayesian inference for average treatment effects

2019/09/26 by Ray, Kolyan, Szabo, Botond · 3 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME)

paper · doi:10.48550/arxiv.1909.12078

Abstract

Bayesian approaches have become increasingly popular in causal inference problems due to their conceptual simplicity, excellent performance and in-built uncertainty quantification ('posterior credible sets'). We investigate Bayesian inference for average treatment effects from observational data, which is a challenging problem due to the missing counterfactuals and selection bias. Working in the standard potential outcomes framework, we propose a data-driven modification to an arbitrary (nonparametric) prior based on the propensity score that corrects for the first-order posterior bias, thereby improving performance. We illustrate our method for Gaussian process (GP) priors using (semi-)synthetic data. Our experiments demonstrate significant improvement in both estimation accuracy and uncertainty quantification compared to the unmodified GP, rendering our approach highly competitive with the state-of-the-art.

Cited by

• A General Bayesian Nonparametric Approach for Estimating Population-Level and Conditional Causal Effects
• Bayesian Semiparametric Causal Inference: Targeted Doubly Robust Estimation of Treatment Effects
• Bayesian Semi-supervised Inference via a Debiased Modeling Approach

Related

• Bayesian Semiparametric Causal Inference: Targeted Doubly Robust Estimation of Treatment Effects
• Double Robust Bayesian Inference on Average Treatment Effects
• A Practical Introduction to Bayesian Estimation of Causal Effects: Parametric and Nonparametric Approaches
• A General Bayesian Nonparametric Approach for Estimating Population-Level and Conditional Causal Effects
• Robust Bayesian Inference of Causal Effects via Randomization Distributions