The Late Pretest Problem in Randomized Control Trials of Education Interventions

Abstract

Pretest–posttest experimental designs often are used in randomized control trials (RCTs) in the education field to improve the precision of the estimated treatment effects. For logistic reasons, however, pretest data often are collected after random assignment, so that including them in the analysis could bias the posttest impact estimates. Thus, the issue of whether to collect and use late pretest data in RCTs involves a variance-bias trade-off. This article addresses this issue both theoretically and empirically for several commonly used impact estimators using a loss function approach that is grounded in the causal inference literature. The key finding is that for RCTs of interventions that aim to improve student test scores, estimators that include late pretests will typically be preferred to estimators that exclude them or that instead include uncontaminated baseline test score data from other sources. This result holds as long as the growth in test score impacts do not grow very quickly early in the school year.