In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation

TL;DR

This paper empirically investigates various model selection criteria for heterogeneous treatment effect estimation, highlighting their strengths, weaknesses, and complex interactions to guide better decision-making in high-stakes applications.

Contribution

It provides a systematic empirical analysis of model selection strategies, revealing their success and failure modes in treatment effect estimation.

Findings

Different selection criteria have distinct success and failure modes.

The interplay between estimators, criteria, and data affects model selection outcomes.

Insights suggest directions for future empirical studies in this area.

Abstract

Personalized treatment effect estimates are often of interest in high-stakes applications -- thus, before deploying a model estimating such effects in practice, one needs to be sure that the best candidate from the ever-growing machine learning toolbox for this task was chosen. Unfortunately, due to the absence of counterfactual information in practice, it is usually not possible to rely on standard validation metrics for doing so, leading to a well-known model selection dilemma in the treatment effect estimation literature. While some solutions have recently been investigated, systematic understanding of the strengths and weaknesses of different model selection criteria is still lacking. In this paper, instead of attempting to declare a global `winner', we therefore empirically investigate success- and failure modes of different selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the data used for comparing them, and provide interesting insights into the relative (dis)advantages of different criteria alongside desiderata for the design of further illuminating empirical studies in this context.