Capturing the severity of type II errors in high-dimensional multiple testing

DOI10.1016/J.JMVA.2015.08.005MaRDI QIDQ893171zbMATH OpenOpenAlexFDO

Authors N. E. Zubov

Publication date 13 November 2015

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.5609

zbMATH Keywords

Bayes rulemultiple testingoracle procedurecompound decision theoryweighted marginal false discovery rateweighted marginal false non-discovery rate

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Bayesian problems; characterization of Bayes procedures (62C10) Paired and multiple comparisons; multiple testing (62J15)

Abstract: The severity of type II errors is frequently ignored when deriving a multiple testing procedure, even though utilizing it properly can greatly help in making correct decisions. This paper puts forward a theory behind developing a multiple testing procedure that can incorporate the type II error severity and is optimal in the sense of minimizing a measure of false non-discoveries among all procedures controlling a measure of false discoveries. The theory is developed under a general model allowing arbitrary dependence by taking a compound decision theoretic approach to multiple testing with a loss function incorporating the type II error severity. We present this optimal procedure in its oracle form and offer numerical evidence of its superior performance over relevant competitors.

Recommendations

• Testing against a high-dimensional alternative in the generalized linear model: asymptotic type I error control
• Accurate error control in high‐dimensional association testing using conditional false discovery rates
• Multiple hypotheses testing and expected number of type I errors
• Accurate inference for repeated measures in high dimensions
• Multiple Comparisons and Type III Errors
• Joint testing and false discovery rate control in high-dimensional multivariate regression
• Improved likelihood ratio tests in a measurement error model for multivariate replicated data
• scientific article; zbMATH DE number 4094579

Cites work

• scientific article; zbMATH DE number 720689 (Why is no real title available?)
• A Bayesian Approach to Multiple Comparisons
• A general decision theoretic formulation of procedures controlling FDR and FNR from a Bayesian perspective
• An exploration of aspects of Bayesian multiple testing
• Classes of orderings of measures and related correlation inequalities. I. Multivariate totally positive distributions
• False discovery control with p-value weighting
• Large-Scale Simultaneous Hypothesis Testing
• Large-scale inference. Empirical Bayes methods for estimation, testing, and prediction
• Large-scale multiple testing under dependence
• Multiple Hypotheses Testing with Weights
• Operating Characteristics and Extensions of the False Discovery Rate Procedure
• Oracle and Adaptive Compound Decision Rules for False Discovery Rate Control
• Power-enhanced multiple decision functions controlling family-wise error and false discovery rates

Cited in

(8)

• Where to find needles in a haystack?
• A multiple testing protocol for exploratory data analysis and the local misclassification rate
• An empirical Bayes testing procedure for detecting variants in analysis of next generation sequencing data
• A new approach to multiple testing of grouped hypotheses
• Local false discovery rate based methods for multiple testing of one-way classified hypotheses
• Weighted False Discovery Rate Control in Large-Scale Multiple Testing
• Constrained Bayesian Rules for Testing Statistical Hypotheses
• Bayesian hidden Markov models for dependent large-scale multiple testing

This page was built for publication: Capturing the severity of type II errors in high-dimensional multiple testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q893171)