Group LASSO Variable Selection Method for Treatment Effect Generalization

TL;DR

This paper introduces a Group LASSO method for selecting variables to improve the generalization of treatment effects from experimental to target populations, addressing heterogeneity and covariate mismatch.

Contribution

It proposes a novel Group LASSO-based approach specifically designed for variable selection in treatment effect generalization problems.

Findings

Applied to low nicotine cigarettes, successfully generalized treatment effects to U.S. smoking population.

Demonstrated effectiveness in selecting relevant variables for heterogeneity modeling.

Improved accuracy in treatment effect estimation across different populations.

Abstract

Often in public health, we are interested in the treatment effect of an intervention on a population that is systemically different from the experimental population the intervention was originally evaluated in. When treatment effect heterogeneity is present in a randomized controlled trial, generalizing the treatment effect from this experimental population to a target population of interest is a complex problem; it requires the characterization of both the treatment effect heterogeneity and the baseline covariate mismatch between the two populations. Despite the importance of this problem, the literature for variable selection in this context is limited. In this paper, we present a Group LASSO-based approach to variable selection in the context of treatment effect generalization, with an application to generalize the treatment effect of very low nicotine content cigarettes to the overall U.S. smoking population.