A Matching Procedure for Sequential Experiments that Iteratively Learns which Covariates Improve Power

TL;DR

This paper introduces a dynamic matching procedure for sequential experiments that adaptively learns which covariates enhance statistical power, leading to more efficient treatment effect estimation in clinical trials.

Contribution

It presents a novel adaptive matching method that improves power and efficiency in sequential randomized trials by learning covariate importance during the experiment.

Findings

Increased statistical power over traditional methods

Effective in simulated and real clinical trial data

Provides an R package for practical implementation

Abstract

We propose a dynamic allocation procedure that increases power and efficiency when measuring an average treatment effect in sequential randomized trials exploiting some subjects' previous assessed responses. Subjects arrive sequentially and are either randomized or paired to a previously randomized subject and administered the alternate treatment. The pairing is made via a dynamic matching criterion that iteratively learns which specific covariates are important to the response. We develop estimators for the average treatment effect as well as an exact test. We illustrate our method's increase in efficiency and power over other allocation procedures in both simulated scenarios and a clinical trial dataset. An R package "SeqExpMatch" for use by practitioners is available.