Control of the mean number of false discoveries, Bonferroni and stability of multiple testing

DOI10.1214/07-AOAS102MaRDI QIDQ995741zbMATHOpenAlexFDO

Authors Galina Glazko, Xing Qiu, Alexander Y. Gordon, A. Y. Yakovlev

Publication date 10 September 2007

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0709.0366

Mathematics Subject Classification ID

Paired and multiple comparisons; multiple testing (62J15)

Abstract: The Bonferroni multiple testing procedure is commonly perceived as being overly conservative in large-scale simultaneous testing situations such as those that arise in microarray data analysis. The objective of the present study is to show that this popular belief is due to overly stringent requirements that are typically imposed on the procedure rather than to its conservative nature. To get over its notorious conservatism, we advocate using the Bonferroni selection rule as a procedure that controls the per family error rate (PFER). The present paper reports the first study of stability properties of the Bonferroni and Benjamini--Hochberg procedures. The Bonferroni procedure shows a superior stability in terms of the variance of both the number of true discoveries and the total number of discoveries, a property that is especially important in the presence of correlations between individual $p$-values. Its stability and the ability to provide strong control of the PFER make the Bonferroni procedure an attractive choice in microarray studies.

Recommendations

• Power and stability comparisons of multiple testing procedures with false discovery rate control
• A Note on Controlling the Number of False Positives
• An improved Bonferroni procedure for multiple tests of significance
• The control of the false discovery rate in multiple testing under dependency.
• Resampling-based multiple testing for microarray data analysis (With comments)

Cited in

(21)

• Familywise and per-family error rates of multiple comparison procedures
• The whole and the parts: the minimum description length principle and the a-contrario framework
• Familywise error rate control via knockoffs
• Simultaneous control of all false discovery proportions in large-scale multiple hypothesis testing
• Outcome-wide longitudinal designs for causal inference: a new template for empirical studies
• Control of the FWER in Multiple Testing Under Dependence
• Testing over a continuum of null hypotheses with false discovery rate control
• Deriving and comparing the distribution for the number of false positives in single step methods to control \(k\)-FWER
• Generalized Augmentation to Control the False Discovery Exceedance in Multiple Testing
• Bayesian analysis of multiple hypothesis testing with applications to microarray experiments
• Asymptotics of Bonferroni for dependent normal test statistics
• Multiple testing in fMRI: an empirical case study on the balance between sensitivity, specificity, and stability
• Multiple Comparisons Controlling Expected Number of False Discoveries
• False discovery variance reduction in large scale simultaneous hypothesis tests
• Diverse correlation structures in gene expression data and their utility in improving statistical inference
• Joint contours, corner and T-junction detection: an approach inspired by the mammal visual system
• False Discovery Rate Estimation for Frequentist Pharmacovigilance Signal Detection Methods
• Sample size and positive false discovery rate control for multiple testing
• Power and stability comparisons of multiple testing procedures with false discovery rate control
• Balancing type one and two errors in multiple testing for differential expression of genes
• A simple approach for local and global variable importance in nonlinear regression models

This page was built for publication: Control of the mean number of false discoveries, Bonferroni and stability of multiple testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q995741)