All Times EDT
Keywords: Observational study, missing data
Conventional controlled clinical trials employ randomization and blinding to ensure the balance of baseline covariates between study arms. The effect of an experimental treatment is formally tested via a pre-specified hypothesis reflecting the study’s primary objective defined by the primary efficacy endpoint, such as, is the experimental treatment effective in reducing cognitive decline at a pre-specified landmark time? To address the same clinical question in an observational study, the targeted maximum likelihood estimation (TMLE) method has been suggested. In this paper presentation, we investigate a prospectively control-matched longitudinal design using longitudinal TMLE via simulation studies. We compare the performance of LTMLE with a few commonly used analysis methods in the presence of missingness. We discuss the results of the simulation studies and their implication to conducting a feasible real-world observational study where missing data cannot be avoided.