Nonparametric Estimation of Mediation Effects with A General Treatment

TL;DR

This paper develops generalized weighting estimators for causal mediation analysis that can handle various types of treatments, demonstrating their consistency, efficiency, and practical effectiveness through simulations and real data.

Contribution

It introduces a unified estimation framework for mediation effects applicable to binary, multi-valued, and continuous treatments, advancing causal mediation analysis methodology.

Findings

Estimators are consistent and asymptotically normal under certain conditions.

Achieves semiparametric efficiency bounds for discrete treatments.

Demonstrates satisfactory finite-sample performance in simulations and real data applications.

Abstract

To investigate causal mechanisms, causal mediation analysis decomposes the total treatment effect into the natural direct and indirect effects. This paper examines the estimation of the direct and indirect effects in a general treatment effect model, where the treatment can be binary, multi-valued, continuous, or a mixture. We propose generalized weighting estimators with weights estimated by solving an expanding set of equations. Under some sufficient conditions, we show that the proposed estimators are consistent and asymptotically normal. Specifically, when the treatment is discrete, the proposed estimators attain the semiparametric efficiency bounds. Meanwhile, when the treatment is continuous, the convergence rates of the proposed estimators are slower than $N^{-1/2}$; however, they are still more efficient than that constructed from the true weighting function. A simulation study reveals that our estimators exhibit a satisfactory finite-sample performance, while an application shows their practical value