A Practical Simulation-Based Method to Calculate Sample Size of Group Sequential Trials for Time-to-Event Data under Exponential and Weibull Distributions

摘要

Group sequential design has been widely applied in clinical trials in the past few decades and the sample size estimation is a vital concern of sponsors and investigators. However, it is a thorny question to survival group sequential trials because of its ambiguous distributional forms, censored data and different definition of information time. And the theoretical approaches seem too complicated to be applied in actual trials. The simulation-based method is a good choice to calculate the sample size due to its simplicity and flexibility.