Robust Causal Learning for the Estimation of Average Treatment Effects

TL;DR

This paper introduces a Robust Causal Learning (RCL) method that improves the stability and accuracy of average treatment effect estimation in observational studies, especially under propensity score misspecification.

Contribution

The paper proposes a theoretically grounded RCL method that addresses error-compounding in DML estimators, providing more stable and reliable causal effect estimates.

Findings

RCL estimators are as consistent and doubly robust as DML.

RCL reduces error-compounding issues in treatment effect estimation.

Empirical results show RCL outperforms traditional methods on various datasets.

Abstract

Many practical decision-making problems in economics and healthcare seek to estimate the average treatment effect (ATE) from observational data. The Double/Debiased Machine Learning (DML) is one of the prevalent methods to estimate ATE in the observational study. However, the DML estimators can suffer an error-compounding issue and even give an extreme estimate when the propensity scores are misspecified or very close to 0 or 1. Previous studies have overcome this issue through some empirical tricks such as propensity score trimming, yet none of the existing literature solves this problem from a theoretical standpoint. In this paper, we propose a Robust Causal Learning (RCL) method to offset the deficiencies of the DML estimators. Theoretically, the RCL estimators i) are as consistent and doubly robust as the DML estimators, and ii) can get rid of the error-compounding issue. Empirically, the comprehensive experiments show that i) the RCL estimators give more stable estimations of the causal parameters than the DML estimators, and ii) the RCL estimators outperform the traditional estimators and their variants when applying different machine learning models on both simulation and benchmark datasets.