Causal machine learning for heterogeneous treatment effects in the presence of missing outcome data

TL;DR

This paper introduces two new de-biased machine learning estimators for heterogeneous treatment effects that effectively handle missing outcome data, improving estimation accuracy in causal inference tasks.

Contribution

It proposes the mDR-learner and mEP-learner, integrating inverse probability of censoring weights into existing estimators to address missing data issues in causal machine learning.

Findings

Estimators are oracle efficient under reasonable conditions.

Simulated data shows improved performance over existing methods.

Application to breast cancer trial demonstrates practical utility.

Abstract

When estimating heterogeneous treatment effects, missing outcome data can complicate treatment effect estimation, causing certain subgroups of the population to be poorly represented. In this work, we discuss this commonly overlooked problem and consider the impact that missing at random (MAR) outcome data has on causal machine learning estimators for the conditional average treatment effect (CATE). We propose two de-biased machine learning estimators for the CATE, the mDR-learner and mEP-learner, which address the issue of under-representation by integrating inverse probability of censoring weights into the DR-learner and EP-learner respectively. We show that under reasonable conditions, these estimators are oracle efficient, and illustrate their favorable performance through simulated data settings, comparing them to existing CATE estimators, including comparison to estimators which use common missing data techniques. We present an example of their application using the GBSG2 trial, exploring treatment effect heterogeneity when comparing hormonal therapies to non-hormonal therapies among breast cancer patients post surgery, and offer guidance on the decisions a practitioner must make when implementing these estimators.