Primary Submission Category: Randomized Designs and Analyses
Rerandomization with Missing Data
Authors: Kateryna Husar, ,
Presenting Author: Kateryna Husar*
Randomized control trials are considered the gold standard in research as they allow for high confidence in establishing cause-and-effect relationships. Randomly assigning participants to the treatment or control group ensures that any observed differences in outcomes between these groups can be attributed to the intervention rather than external factors. Yet, differences between the groups can still occur due to chance, potentially resulting in misleading results. The issue of observed covariate imbalance can be addressed in the design phase: rerandomization selects a treatment assignment from a subset of assignments that satisfy a predetermined balance criterion for pre-treatment covariates. Under rerandomization, classical estimators yield a more precise estimator and combining rerandomization with the regression adjustment can further improve inference. In practice, even in the pre-treatment stage, there may be substantial missing data, which in turn can reduce the improvements due to rerandomization and cannot be addressed by simple post-hoc regression adjustment. By introducing missing data imputation methods into the rerandomization, we recover the efficiency losses for estimating average treatment effects. We show how rerandomization that adjusts for missingness combined with regression adjustment increases the precision of the estimates compared to regression adjustment alone and recommend the use of rerandomization in the study design when missing data are present.