Testing Full Mediation of Treatment Effects and the Identifiability of Causal Mechanisms

TL;DR

This paper introduces a statistical test for assessing whether a treatment's effect is fully mediated by observed intermediates and whether causal mechanisms are identifiable, applicable to both randomized and non-randomized settings.

Contribution

It develops a novel test for full mediation and causal mechanism identifiability, extending to high-dimensional covariates with a double machine learning approach.

Findings

Test successfully distinguishes full mediation in simulations.

Method performs well with high-dimensional covariates.

Empirical applications demonstrate practical utility.

Abstract

In causal analysis, understanding the causal mechanisms through which an intervention or treatment affects an outcome is often of central interest. We propose a test to evaluate (i) whether the causal effect of a treatment that is randomly assigned conditional on covariates is fully mediated by, or operates exclusively through, observed intermediate outcomes (referred to as mediators or surrogate outcomes), and (ii) whether the various causal mechanisms operating through different mediators are identifiable conditional on covariates. We demonstrate that if both full mediation and identification of causal mechanisms hold, then the conditionally random treatment is conditionally independent of the outcome given the mediators and covariates. Furthermore, we extend our framework to settings with non-randomly assigned treatments. We show that, in this case, full mediation remains testable, while identification of causal mechanisms is no longer guaranteed. We propose a double machine learning framework for implementing the test that can incorporate high-dimensional covariates and is root-n consistent and asymptotically normal under specific regularity conditions. We also present a simulation study demonstrating good finite-sample performance of our method, along with two empirical applications revisiting randomized experiments on maternal mental health and social norms.