Hsiao-Hui Tsou
Institute of Population Health Sciences, National Health Research Institutes
![IconGems-Print](images/IconGems-Print.png)
337 – Interim Monitoring and Analyses: Two-Stage, Multi-Stage, and Group Sequential Designs
Strategies in Designing Interim Analyses Under Discrete Random-Effects Model in a Multiregional Trial
Hsiao-Hui Tsou
Institute of Population Health Sciences, National Health Research Institutes
Chi-Tian Chen
Institute of Population Health Sciences
K.K. Gordon Lan
Janssen R & D, Pharmaceutical Companies of Johnson & Johnson
When designing a trial, the sample size is usually estimated from limited information. It would be desirable to modify total sample size or adjust sample size allocation using accumulated data for increasing the efficiency of clinical trials. In this research, we focus on the design of a multiregional trial since developing pharmaceutical products via multiregional clinical trials has become a preferred strategy. We consider a discrete random effects model to account for heterogeneous treatment effect across regions. We propose some strategies for sample size re-estimation or sample size re-allocation to increase the efficiency of a clinical trial based on interim data.