Matching Algorithms for Causal Inference with Multiple Treatments

TL;DR

This paper introduces new matching algorithms for causal inference with multiple treatments, improving covariate balance and providing guidance on their application in observational studies.

Contribution

It proposes novel matching algorithms tailored for multiple treatments, addressing limitations of existing methods and enhancing covariate balance in causal effect estimation.

Findings

All methods improved covariate balance over pre-matching data.

Simulations demonstrate advantages of new algorithms over existing ones.

Guidelines provided for selecting matching algorithms based on covariate distributions.

Abstract

Randomized clinical trials (RCTs) are ideal for estimating causal effects, because the distributions of background covariates are similar in expectation across treatment groups. When estimating causal effects using observational data, matching is a commonly used method to replicate the covariate balance achieved in a RCT. Matching algorithms have a rich history dating back to the mid-1900s, but have been used mostly to estimate causal effects between two treatment groups. When there are more than two treatments, estimating causal effects requires additional assumptions and techniques. We propose matching algorithms that address the drawbacks of the current methods, and we use simulations to compare current and new methods. All of the methods display improved covariate balance in the matched sets relative to the pre-matched cohorts. In addition, we provide advice to investigators on which matching algorithms are preferred for different covariate distributions.