Omnibus Permutation Tests of the Overall Null Hypothesis in Datasets with Many Covariates

• Published in: Journal of biopharmaceutical statistics Vol. 16; no. 3; pp. 327 - 341
• Main Authors: Potter, Douglas M., Griffiths, Derek J.
• Format: Journal Article
• Language: English
• Published: England Taylor & Francis Group 01.05.2006
• Subjects: Combining functions; Computer Simulation; Data Interpretation, Statistical; Gene Expression Profiling - methods; Glucose Intolerance - genetics; Glucose Intolerance - metabolism; Humans; Male; Mandelic Acids - therapeutic use; Models, Statistical; Omnibus test; Overall null hypotheses; Oxidative Phosphorylation; Parasympatholytics - therapeutic use; Permutation test; Randomized Controlled Trials as Topic - methods; Regression Analysis; Research Design; Statistics, Nonparametric; Urinary Incontinence - drug therapy
• ISSN: 1054-3406; 1520-5711
• DOI: 10.1080/10543400600609585

Tests of the overall null hypothesis in datasets with one outcome variable and many covariates can be based on various methods to combine the p-values for univariate tests of association of each covariate with the outcome. The overall p-value is computed by permuting the outcome variable. We discuss the situations in which this approach is useful and provide several examples. We use simulations to investigate seven omnibus test statistics and find that the Anderson-Darling and Fisher's statistics are superior to the others.