Hochbergs step-up method: Cutting corners off holms step-down method

• 成果类型: Article
• 署名作者: Huang, Yifan; Hsu, Jason C.
• 署名单位: State University System of Florida; University of South Florida; University System of Ohio; Ohio State University
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/asm067
• 发表日期: 2007
• 页码: 965975
• 关键词: remitting multiple-sclerosis; placebo-controlled trial; interferon beta-1b; BONFERRONI PROCEDURE; DOUBLE-BLIND; inequalities; multicenter; variables; tests

摘要

Holm's method and Hochberg's method for multiple testing can be viewed as step-down and step-up versions of the Bonferroni test. We show that both are special cases of partition testing. The difference is that, while Holm's method tests each partition hypothesis using the largest order statistic, setting a critical value based on the Bonferroni inequality, Hochberg's method tests each partition hypothesis using all the order statistics, setting a series of critical values based on Simes' inequality. Geometrically, Hochberg's step-upmethod 'cuts corners' off the acceptance regions of Holm's step-down method by making assumptions on the joint distribution of the test statistics. As can be expected, partition testing making use of the joint distribution of the test statistics is more powerful than partition testing using probabilistic inequalities. Thus, if the joint distribution of the test statistics is available, through modelling for example, we recommend partition step-down testing, setting exact critical values based on the joint distribution.