Technical Note: Targeted Maximum Likelihood Estimator for an ATE Standardized for New Target Population

TL;DR

This paper introduces a targeted maximum likelihood estimator (TMLE) for transporting the average treatment effect (ATE) from a source to a target population, accounting for covariate differences, missing data, and censoring.

Contribution

It develops a TMLE framework for estimating the ATE in a target population using data from a source population, accommodating covariate limitations, missingness, and censoring.

Findings

Derivation of canonical gradients for the estimator

Development of TMLEs for clinical outcomes with missingness

Extension to time-to-event outcomes with censoring

Abstract

In this technical note we present a targeted maximum likelihood estimator (TMLE) for a previously studied target parameter that aims to transport an average treatment effect (ATE) on a clinical outcome in a source population to what the ATE would have been in another target population. It is assumed that one only observes baseline covariates in the target population, while we assume that one can learn the conditional treatment effect on the outcome of interest in the source population. We also allow that one might observe only a subset of the covariates in the target population while all covariates are measured in the source population. We consider the case that the outcome is a clinical outcome at some future time point that is subject to missingness, or that our outcome of interest is a time to event that is subject to right-censoring. We derive the canonical gradients and present the corresponding TMLEs for these two cases.