Quasi-Oracle Estimation of Heterogeneous Treatment Effects

TL;DR

This paper introduces a flexible two-step method for estimating heterogeneous treatment effects that achieves near-oracle accuracy even with imperfect initial estimates, applicable with various machine learning techniques.

Contribution

The paper proposes a novel two-step estimation framework that is adaptable, easy to implement, and achieves quasi-oracle properties in treatment effect estimation.

Findings

Method performs well with penalized regression, kernel ridge regression, and boosting.

Achieves error bounds comparable to an oracle with perfect nuisance component knowledge.

Demonstrates promising results in simulation studies.

Abstract

Flexible estimation of heterogeneous treatment effects lies at the heart of many statistical challenges, such as personalized medicine and optimal resource allocation. In this paper, we develop a general class of two-step algorithms for heterogeneous treatment effect estimation in observational studies. We first estimate marginal effects and treatment propensities in order to form an objective function that isolates the causal component of the signal. Then, we optimize this data-adaptive objective function. Our approach has several advantages over existing methods. From a practical perspective, our method is flexible and easy to use: In both steps, we can use any loss-minimization method, e.g., penalized regression, deep neural networks, or boosting; moreover, these methods can be fine-tuned by cross validation. Meanwhile, in the case of penalized kernel regression, we show that our method has a quasi-oracle property: Even if the pilot estimates for marginal effects and treatment propensities are not particularly accurate, we achieve the same error bounds as an oracle who has a priori knowledge of these two nuisance components. We implement variants of our approach based on penalized regression, kernel ridge regression, and boosting in a variety of simulation setups, and find promising performance relative to existing baselines.