Chen Xun, Luo Xiaohui, Capizzi Tom
Clinical Biostatistics, Merck Research Laboratories, RY34-A316, Rahway, NJ 07065, USA.
Stat Med. 2005 May 15;24(9):1385-97. doi: 10.1002/sim.2005.
The parallel gatekeeping strategy proposed by Dmitrienko et al. (Statist. Med. 2003; 22:2387-2400) provides a flexible framework for the pursuit of strong control on study wise type I error rate. This paper further explores the application of the weighted Simes parallel gatekeeping procedure recommended by Dmitrienko et al. and proposes some modifications to it to better incorporate the interrelationships of different hypotheses in actual clinical trials and to achieve better power performance. We first propose a simple method to quantitatively control the impact of secondary tests on the testing of primary hypotheses. We then introduce a matched gatekeeping procedure to exemplify how to address special relationships between individual primary and secondary tests following the parallel gatekeeping framework. Our simulation study demonstrates that the enhanced gatekeeping procedures generally result in more powerful tests than the parallel gatekeeping procedure in Dmitrienko et al. whenever applicable.
德米特里延科等人（《统计医学》，2003年；22:2387 - 2400）提出的平行把关策略为严格控制研究层面的I型错误率提供了一个灵活的框架。本文进一步探讨了德米特里延科等人推荐的加权西姆斯平行把关程序的应用，并对其提出了一些修改建议，以便在实际临床试验中更好地纳入不同假设之间的相互关系，并实现更好的检验效能表现。我们首先提出一种简单的方法来定量控制次要检验对主要假设检验的影响。然后我们引入一种匹配把关程序，以举例说明如何在平行把关框架下处理各个主要和次要检验之间的特殊关系。我们的模拟研究表明，在适用的情况下，增强后的把关程序通常比德米特里延科等人提出的平行把关程序具有更强的检验效能。
