New multivariate tests for assessing covariate balance in matched observational studies

TL;DR

This paper introduces new multivariate tests for evaluating covariate balance in matched observational studies, demonstrating high power and practical applicability with an R package, especially for large datasets.

Contribution

The paper develops novel multivariate balance tests with superior power and provides an R implementation, improving assessment of covariate balance in observational research.

Findings

Tests exhibit high power under various alternatives.

Asymptotic null distributions enable accurate p-value calculation.

Application to smoking and blood lead levels demonstrates practical utility.

Abstract

We propose new tests for assessing whether covariates in a treatment group and matched control group are balanced in observational studies. The tests exhibit high power under a wide range of multivariate alternatives, some of which existing tests have little power for. The asymptotic permutation null distributions of the proposed tests are studied and the p-values calculated through the asymptotic results work well in finite samples, facilitating the application of the test to large data sets. The tests are illustrated in a study of the effect of smoking on blood lead levels. The proposed tests are implemented in an R package BalanceCheck.