The closure principle is fundamental in multiple testing and has been used to derive many efficient procedures with familywise error rate control. However, it is often not suitable for modern research, as more flexible multiple testing settings are considered where not all hypotheses are known at the beginning of the evaluation. In this paper, we focus on online multiple testing where a possibly infinite sequence of hypotheses is tested over time. At each step, it must be decided on the current hypothesis without having any information about the hypotheses that have not been tested yet. Our main contribution is a new online closure principle which ensures that the resulting closed procedure can be applied in the online setting. We prove that any familywise error rate (FWER) controlling online procedure can be derived by this online closure principle. In addition, we demonstrate how short-cuts of these online closed procedures can be obtained under a suitable consonance property and apply the results in order to construct new online multiple testing methods. Finally, the new online closure principle is used to derive an improvement of the currently most promising online procedure with FWER control, the ADDIS-Spending under local dependence.
翻译:关闭原则在多个测试中具有根本意义,并被用于产生许多有效的程序,同时对家庭错误率进行控制。然而,它往往不适合现代研究,因为如果在评估开始时并非所有假设都已知,则考虑更灵活的多重测试设置。在本文中,我们侧重于在线多重测试,对可能无限的假设序列进行长期测试。在每一步骤中,都必须就目前的假设作出决定,而没有关于尚未测试的假设的任何信息。我们的主要贡献是一项新的在线关闭原则,确保由此产生的封闭程序能够在在线环境中应用。我们证明,任何基于家庭原因的错误率(FWER)控制在线程序都可以从这一在线关闭原则中推断出来。此外,我们演示这些在线封闭程序如何在适当的连接属性下获得短切的,并应用结果来构建新的在线多重测试方法。最后,新的在线关闭原则被用来改进目前最有希望的在线程序,即FWER控制,ADDDIS-S在本地依赖下。