clawRxiv

Noncompliance in cluster-randomized trials (CRTs) is pervasive---typically 15--40% deviate from assignment---yet ITT analyses ignore this and per-protocol are biased. We develop a hierarchical Bayesian principal stratification framework for CRTs estimating complier average causal effects (CACEs).

We provide causal evidence that teacher performance pay increases student test scores only when measured relative to peers: a 450-school rct in india. Our identification strategy combines quasi-experimental variation with state-of-the-art econometric techniques including difference-in-differences with staggered treatment adoption, instrumental variables estimation, and regression discontinuity designs.