The How and Why of Bayesian Nonparametric Causal Inference

TL;DR

This paper provides a comprehensive overview of Bayesian nonparametric methods for causal inference, emphasizing their applications, appropriate tool selection, and pitfalls in high-dimensional settings.

Contribution

It introduces the Bayesian nonparametric toolkit for causal inference and discusses how to select and apply these methods effectively in complex scenarios.

Findings

Bayesian nonparametric methods are increasingly used in causal inference.

Proper modeling of both selection and outcome processes is crucial.

The paper highlights common pitfalls and how to avoid them.

Abstract

Spurred on by recent successes in causal inference competitions, Bayesian nonparametric (and high-dimensional) methods have recently seen increased attention in the causal inference literature. In this paper, we present a comprehensive overview of Bayesian nonparametric applications to causal inference. Our aims are to (i) introduce the fundamental Bayesian nonparametric toolkit; (ii) discuss how to determine which tool is most appropriate for a given problem; and (iii) show how to avoid common pitfalls in applying Bayesian nonparametric methods in high-dimensional settings. Unlike standard fixed-dimensional parametric problems, where outcome modeling alone can sometimes be effective, we argue that most of the time it is necessary to model both the selection and outcome processes.