B1080
Title: Power and sample size calculations for rerandomized experiments
Authors: Zach Branson - Carnegie Mellon University (United States) [presenting]
Xinran Li - University of Illinois Urbana-Champaign (United States)
Peng Ding - University of California, Berkeley (United States)
Abstract: Power analyses are an important aspect of experimental design, because they help determine how experiments are implemented. 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 than complete randomization, in the sense that it can have a lower Type-I error, 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.
