Power and Sample Size Calculations for Rerandomization

TL;DR

This paper develops power and sample size calculations for rerandomized experiments, revealing that rerandomization generally increases power but can reduce it for very small effects due to increased conservativeness and treatment effect heterogeneity.

Contribution

It establishes the power of rerandomized experiments, providing a new tool for sample size calculation and highlighting the nuanced effects of heterogeneity on power.

Findings

Power is often higher under rerandomization than complete randomization.

For very small treatment effects, rerandomization can decrease power.

Heterogeneity influences power differently depending on effect size.

Abstract

Power analyses are an important aspect of experimental design, because they help determine how experiments are implemented in practice. It is common to specify a desired level of power and compute the sample size necessary to obtain that power. Such calculations are well-known for completely randomized experiments, but there can be many benefits to using other experimental designs. For example, it has recently been established that rerandomization, where subjects are randomized until covariate balance is obtained, increases the precision of causal effect estimators. This work establishes the power of rerandomized treatment-control experiments, thereby allowing for sample size calculators. We find the surprising result that, while power is often greater under rerandomization than complete randomization, the opposite can occur for very small treatment effects. The reason is that inference under rerandomization can be relatively more conservative, in the sense that it can have a lower type-I error at the same nominal significance level, and this additional conservativeness adversely affects power. This surprising result is due to treatment effect heterogeneity, a quantity often ignored in power analyses. We find that heterogeneity increases power for large effect sizes but decreases power for small effect sizes.