On the Design and Analysis of Multiarmed Adaptive Trials
View Presentation View Presentation
*Gernot Wassmer, IMSIE 

Keywords: multiarmed design, multiple comparison, closed test procedure

In multiarmed clinical trials, treatment selection and sample size reassessment are straightforward and attractive applications when using an adaptive test design. Generally, when considering more than two treatment arms, often Dunnett's test is applied, but other testing procedures can also be used, e.g., Bonferroni tests, Simes tests, etc. An adaptive test procedure can be based on the closed testing procedure and the inverse normal method for combining the stage results of the trial. This procedure can also be used for survival data where the test utilizes the independent increment property of the log-rank test statistic. In the talk, the recently proposed procedures and designing options relevant for assessing the statistical performance of such designs are given.