The false discovery rate for statistical pattern recognition

DOI10.1214/09-EJS363zbMATH Open1326.62141arXiv0901.4184OpenAlexW2087245956MaRDI QIDQ1951997FDOQ1951997

Authors: Clayton Scott, Gowtham Bellala, Rebecca Willett 

Publication date: 27 May 2013

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: The false discovery rate (FDR) and false nondiscovery rate (FNDR) have received considerable attention in the literature on multiple testing. These performance measures are also appropriate for classification, and in this work we develop generalization error analyses for FDR and FNDR when learning a classifier from labeled training data. Unlike more conventional classification performance measures, the empirical FDR and FNDR are not binomial random variables but rather a ratio of binomials, which introduces challenges not addressed in conventional analyses. We develop distribution-free uniform deviation bounds and apply these to obtain finite sample bounds and strong universal consistency.

Full work available at URL: https://arxiv.org/abs/0901.4184

Recommendations

• On a generalized false discovery rate
• Estimating the false discovery rate using the stochastic approximation algorithm
• False discovery rate for scanning statistics
• False discovery rate approach to dynamic change detection
• A Direct Approach to False Discovery Rates
• The false discovery rate: a variable selection perspective
• False discovery rate envelopes
• Learning false discovery rates by fitting sigmoidal threshold functions
• False discovery rate estimation for large-scale homogeneous discrete \(p\)-values

zbMATH Keywords

false discovery rategeneralization errorstatistical learning theory

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Title not available (Why is that?)
• Higher criticism for detecting sparse heterogeneous mixtures.
• A Direct Approach to False Discovery Rates
• Probability Inequalities for Sums of Bounded Random Variables
• An algorithm for information structuring and retrieval
• Empirical Bayes Analysis of a Microarray Experiment
• Title not available (Why is that?)
• Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector
• The positive false discovery rate: A Bayesian interpretation and the \(q\)-value
• Ranking and empirical minimization of \(U\)-statistics
• Title not available (Why is that?)
• Combinatorial methods in density estimation
• Optimal aggregation of classifiers in statistical learning.
• Generalization bounds for the area under the ROC curve
• Advanced Lectures on Machine Learning
• Learning minimum volume sets
• A Neyman–Pearson Approach to Statistical Learning
• Some PAC-Bayesian theorems
• Considering cost asymmetry in learning classifiers
• Performance Measures for Neyman–Pearson Classification
• Positive false discovery proportions: intrinsic bounds and adaptive control
• Error-correcting tournaments
• Occam’s Hammer
• Transductive Rademacher Complexity and Its Applications

Cited In (8)

• A multiple testing protocol for exploratory data analysis and the local misclassification rate
• Binary classification with pFDR-pFNR losses
• Fisher’s Conditionality Principle in Statistical Pattern Recognition
• False Discovery Rates for Spatial Signals
• On false discovery rate thresholding for classification under sparsity
• Error rate control for classification rules in multiclass mixture models
• False discovery rate approach to dynamic change detection
• Title not available (Why is that?)

This page was built for publication: The false discovery rate for statistical pattern recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1951997)