Conference Program

Validity of Tests for Time-to-Event Endpoints in Studies with the Pocock and Simon’s Minimization (303691)

View Presentation

Michael Gekhtman, University of Notre Dame 
*Victoria Plamadeala Johnson, GSK 
Olga Kuznetsova, Merck & Co., Inc. 
Michael Proschan, National Institute of Allergy and Infectious Diseases, NIH 
Ting Ye, University of Washington 

Keywords: minimization, Pocock and Simon covariate-adaptive randomization, Type I error, log-rank test, robust survival analysis tests

Model misspecification caused by the omission of some factors from the analysis model is more common in trials when the Pocock and Simon’s minimization is warranted. Recent work by Johnson, Gekhtman and Kuznetsova (draft manuscript, 2022) extends the theory developed by Ye and Shao (2020) to show that both the log-rank and the robust score tests are conservative under minimization if the model is misspecified. This confirms the results of previous simulations by multiple authors, including Ye and Shao (2020), that showed the conservativeness of the log-rank test following the Pocock and Simon’s minimization.