A1042
Title: Inference on tree-structured subgroups with subgroup size and subgroup effect relationship in clinical trials
Authors: Yuanhui Luo - The Hong Kong University of Science and Technology (Hong Kong) [presenting]
Xinzhou Guo - The Hong Kong University of Science and Technology (Hong Kong)
Abstract: When multiple candidate subgroups are considered in clinical trials, it is often necessary to make statistical inferences on the subgroups simultaneously. Classical multiple testing procedures might not lead to an interpretable and efficient inference on the subgroups as they often fail to take the subgroup size and subgroup effect relationship into account. Built on the selective traversed accumulation rules (STAR), a data-adaptive and interactive multiple-testing procedure is proposed for subgroups, which can take subgroup size and subgroup effect relationship into account under a prespecified tree structure. The proposed method is easy to implement and can lead to a more interpretable and efficient inference on prespecified tree-structured subgroups. The merit of the proposed method is demonstrated by re-analyzing the panitumumab trial with the proposed method.
