Detection of correlations

DOI10.1214/11-AOS964zbMATH Open1246.62142arXiv1106.1193OpenAlexW3104928457MaRDI QIDQ450041FDOQ450041

Authors: Ery Arias-Castro, Sébastien Bubeck, Gábor Lugosi 

Publication date: 3 September 2012

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

Abstract: We consider the hypothesis testing problem of deciding whether an observed high-dimensional vector has independent normal components or, alternatively, if it has a small subset of correlated components. The correlated components may have a certain combinatorial structure known to the statistician. We establish upper and lower bounds for the worst-case (minimax) risk in terms of the size of the correlated subset, the level of correlation, and the structure of the class of possibly correlated sets. We show that some simple tests have near-optimal performance in many cases, while the generalized likelihood ratio test is suboptimal in some important cases.

Full work available at URL: https://arxiv.org/abs/1106.1193

Recommendations

• scientific article; zbMATH DE number 1495742
• Extracting correlations
• Detecting positive correlations in a multivariate sample
• Detecting a path of correlations in a network
• scientific article; zbMATH DE number 1551916
• Correlation and dependence
• Correlation measures
• Detection of Correlations With Adaptive Sensing

zbMATH Keywords

generalized likelihood ratio testsparse covariance matrixscan statisticBayesian detectionminimax detection

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Measures of association (correlation, canonical correlation, etc.) (62H20)

Cites Work

• Testing Statistical Hypotheses
• Covariance regularization by thresholding
• Minimax detection of a signal for \(l^ n\)-balls.
• Higher criticism for detecting sparse heterogeneous mixtures.
• Detection of an anomalous cluster in a network
• Innovated higher criticism for detecting sparse signals in correlated noise
• Non-asymptotic minimax rates of testing in signal detection
• Optimal detection of heterogeneous and heteroscedastic mixtures
• False Discovery Control for Random Fields
• Optimal rates of convergence for covariance matrix estimation
• On combinatorial testing problems
• Near-Optimal Detection of Geometric Objects by Fast Multiscale Methods
• Searching for a trail of evidence in a maze
• Maximal meaningful events and applications to image analysis
• Detection of stochastic processes
• On the asymptotic distribution of the discrete scan statistic
• High-dimensional random geometric graphs and their clique number
• Title not available (Why is that?)
• Detection of Spatially Correlated Gaussian Time Series
• Detection of Gauss–Markov Random Fields With Nearest-Neighbor Dependency

Cited In (19)

• Sequential subspace change point detection
• Combinatorial inference for graphical models
• Detecting Markov random fields hidden in white noise
• Statistical and computational limits for sparse matrix detection
• Optimal testing for planted satisfiability problems
• Detecting positive correlations in a multivariate sample
• Fast nonasymptotic testing and support recovery for large sparse Toeplitz covariance matrices
• Tests alternative to higher criticism for high-dimensional means under sparsity and column-wise dependence
• Direct evaluation of the desired correlations: verification on real data
• Detecting a path of correlations in a network
• Innovated higher criticism for detecting sparse signals in correlated noise
• Joint sequential detection and isolation for dependent data streams
• Indirect determination of correlation
• Testing and signal identification for two-sample high-dimensional covariances via multi-level thresholding
• Optimal detection of sparse principal components in high dimension
• Sharp optimality for high-dimensional covariance testing under sparse signals
• Property testing in high-dimensional Ising models
• Title not available (Why is that?)
• Optimality and sub-optimality of PCA. I: Spiked random matrix models

This page was built for publication: Detection of correlations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q450041)