Biostatistics Journal Club: Handling Missing Data in Cluster Randomized Trials

In cluster-randomized trials, missing data can occur in various ways, including missing outcomes and baseline covariates at either the individual or cluster level. In this talk, Rui Wang, PhD, Harvard Pilgrim Health Care Institute, will discuss methods for estimating the average treatment effect and intraclass correlation coefficients using weighted generalized estimating equations. These estimators can handle missing outcomes under the missing-at-random assumption and accommodate missing covariates without imposing restrictions on the missingness mechanism. Wang will also discuss some considerations to improve precision by leveraging machine learning and modeling the treatment assignment mechanism, as well as approaches for sensitivity analysis to assess the robustness of results when missing data assumptions are violated.

Speaker:

Rui Wang, PhD, Harvard Pilgrim Health Care Institute