arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.12447stat.MEmath.STstat.TH
收藏

多重检验中作为非归一化权重的 e-values

E-values as unnormalized weights in multiple testing

Nikolaos Ignatiadis, Ruodu Wang, Aaditya Ramdas

AI总结:

本文研究 p-values 与 e-values 结合的多重检验问题,证明独立 e-values 作为数据驱动权重时无需归一化,并提出可在元分析或单一数据中实现的高功效检验程序。

摘要:

我们研究如何结合 p-values 与 e-values,并在每个假设都同时具备 p-values 和 e-values 的情况下设计多重检验程序。我们的结果为使用数据驱动权重的多重检验提供了新视角:标准加权多重检验方法要求权重确定性地相等于待检验假设的数量,而我们证明,当权重是独立于 p-values 的 e-values 时,并不需要这种归一化。此类 e-values 可在元分析设置中获得,即用主数据集计算 p-values,并用独立的辅助数据集计算 e-values。除元分析外,我们还展示了可在单一数据集上构造相互独立的 e-values 和 p-values 的情形。我们的程序可显著提高检验功效,尤其是在非零假设的 e-values 远大于一时。

英文摘要:

We study how to combine p-values and e-values, and design multiple testing procedures where both p-values and e-values are available for every hypothesis. Our results provide a new perspective on multiple testing with data-driven weights: while standard weighted multiple testing methods require the weights to deterministically add up to the number of hypotheses being tested, we show that this normalization is not required when the weights are e-values that are independent of the p-values. Such e-values can be obtained in the meta-analysis setting wherein a primary dataset is used to compute p-values, and an independent secondary dataset is used to compute e-values. Going beyond meta-analysis, we showcase settings wherein independent e-values and p-values can be constructed on a single dataset itself. Our procedures can result in a substantial increase in power, especially if the non-null hypotheses have e-values much larger than one.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑