Presented by Laura Balzer, Assistant Professor of Biostatistics and Director of the Causality Lab at UMass Amherst, based on a recent publication, arxiv.org/abs/... . Cluster randomized trials (CRTs) randomly assign an intervention to groups of individuals (e.g., clinics or communities), and measure outcomes on individuals in those groups. While offering many advantages, this experimental design introduces challenges that are only partially addressed by existing analytic approaches. First, outcomes are often missing for some individuals within clusters. Failing to appropriately adjust for differential outcome measurement can result in bias. Second, CRTs often randomize limited numbers of clusters, resulting in chance imbalances on baseline outcome predictors between arms. Failing to adaptively adjust for these imbalances can result in efficiency losses. To address these methodological gaps, we propose and evaluate a novel Two-Stage targeted minimum loss-based estimator (TMLE) to adjust for covariate imbalance in a manner that optimizes precision, after controlling for baseline and post-baseline causes of missing outcomes.
17 сен 2024
