In self-designing clinical trials, a special case of adaptive group sequential experiments, a confidence interval for the difference of normal means is derived, in which the results of the respective study stages are combined using the weighted inverse normal method. During the course of the self-designing trial, the sample sizes as well as the number of study stages can be simultaneously determined in a completely adaptive way. Practical rules for updating sample sizes and assigning weights to the study stages are presented. The implementation of the self-designing trial and the resulting confidence interval are demonstrated using real data.
Study Stage Equal Sample Size Adaptive Planning Adaptive Group Pivotal Statistic
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.
This paper is based on some earlier joint work with Joachim Hartung.
Cheng, Y., Shen, Y.: Estimation of a parameter and its exact confidence interval following sequential sample size reestimation trials. Biometrics 60, 910–918 (2004)CrossRefzbMATHMathSciNetGoogle Scholar
EMEA (The European Agency for the Evaluation of Medicinal Products) Points to Consider on Switching between Superiority and Non-inferiority. London, CPMP/EWP/482/99 (2000)Google Scholar