Premium
Hypothesis testing for two‐stage designs with over or under enrollment
Author(s) -
Zeng Donglin,
Gao Fei,
Hu Kuolung,
Jia Catherine,
Ibrahim Joseph G.
Publication year - 2015
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.6490
Subject(s) - sample size determination , type i and type ii errors , inference , confidence interval , computer science , statistics , computation , stage (stratigraphy) , sample (material) , multiple comparisons problem , statistical hypothesis testing , power (physics) , mathematics , algorithm , artificial intelligence , paleontology , chemistry , chromatography , biology , physics , quantum mechanics
Simon's two‐stage designs are widely used in cancer phase II clinical trials for assessing the efficacy of a new treatment. However in practice, the actual sample size for the second stage is often different from the planned sample size, and the original inference procedure is no longer valid. Previous work on this problem has certain limitations in computation. In this paper, we attempt to maximize the unconditional power while controlling for the type I error for the modified second stage sample size. A normal approximation is used for computing the power, and the numerical results show that the approximation is accurate even under small sample sizes. The corresponding confidence intervals for the response rate are constructed by inverting the hypothesis test, and they have reasonable coverage while preserving the type I error. Copyright © 2015 John Wiley & Sons, Ltd.