Optimal rank-based testing for principal components

DOI10.1214/10-AOS810zbMATH Open1373.62295arXiv1211.2117OpenAlexW2029643397MaRDI QIDQ620547FDOQ620547

Authors: Marc Hallin, Davy Paindaveine, Thomas Verdebout 

Publication date: 19 January 2011

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

Abstract: This paper provides parametric and rank-based optimal tests for eigenvectors and eigenvalues of covariance or scatter matrices in elliptical families. The parametric tests extend the Gaussian likelihood ratio tests of Anderson (1963) and their pseudo-Gaussian robustifications by Davis (1977) and Tyler (1981, 1983). The rank-based tests address a much broader class of problems, where covariance matrices need not exist and principal components are associated with more general scatter matrices. The proposed tests are shown to outperform daily practice both from the point of view of validity as from the point of view of efficiency. This is achieved by utilizing the Le Cam theory of locally asymptotically normal experiments, in the nonstandard context, however, of a curved parametrization. The results we derive for curved experiments are of independent interest, and likely to apply in other contexts.

Full work available at URL: https://arxiv.org/abs/1211.2117

Recommendations

• Optimal rank-based tests for common principal components
• A class of asymptotic tests for principal component vectors
• Optimal rank-based tests for homogeneity of scatter
• Principal component decomposition of non-parametric tests
• Optimal signed-rank tests based on hyperplanes
• A rank-based high-dimensional test for equality of mean vectors
• scientific article; zbMATH DE number 3940477
• Generalized reduced rank tests using the singular value decomposition

zbMATH Keywords

principal componentslocal asymptotic normalityscatter matrixcurved experimentselliptical densitiesmultivariate ranks and signsshape matrixtests for eigenvaluestests for eigenvectors

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Nonparametric robustness (62G35) Factor analysis and principal components; correspondence analysis (62H25)

Cites Work

• Asymptotic Statistics
• Title not available (Why is that?)
• A distribution-free M-estimator of multivariate scatter
• Asymptotics of eigenvalues and unit-length eigenvectors of sample variance and correlation matrices
• Asymptotics in statistics. Some basic concepts.
• Optimal predictive model selection.
• Semiparametrically efficient rank-based inference for shape. I: optimal rank-based tests for sphericity
• Semiparametrically efficient rank-based inference for shape. II: Optimal \(R\)-estimation of shape
• Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies
• Principal Components Analysis Based on Multivariate MM Estimators With Fast and Robust Bootstrap
• Asymptotic methods in statistical decision theory
• Mathematical theory of statistics. Statistical experiments and asymptotic decision theory
• Empirical Bayes Analysis of a Microarray Experiment
• Title not available (Why is that?)
• A canonical definition of shape
• Asymptotic Theory for Principal Component Analysis
• Title not available (Why is that?)
• Aligned rank tests for linear models with autocorrelated error terms
• Optimal tests for multivariate location based on interdirections and pseudo-Mahalanobis ranks.
• Asymptotic distributions in canonical correlation analysis and other multivariate procedures for nonnormal populations
• On adaptive estimation in stationary ARMA processes
• Rank-based optimal tests of the adequacy of an elliptic VARMA model
• The effects of nonnormality on asymptotic distributions of some likelihood ratio criteria for testing covariance structures under normal assumption
• A Test for a Specific Principal Component of a Correlation Matrix
• Analysis of Covariance Structures Under Elliptical Distributions
• Affine-invariant aligned rank tests for the multivariate general linear model with VARMA errors
• Semi-parametric efficiency, distribution-freeness and invariance
• Asymptotic inference for eigenvectors
• Title not available (Why is that?)
• A class of asymptotic tests for principal component vectors
• ASYMPTOTIC THEORY FOR PRINCIPAL COMPONENT ANALYSIS: NON-NORMAL CASE1
• Parametric and semiparametric inference for shape: the role of the scale functional
• A Chernoff-Savage result for shape: On the non-admissibility of pseudo-Gaussian methods
• Optimal rank-based tests for homogeneity of scatter

Cited In (27)

• Optimal tests for elliptical symmetry: specified and unspecified location
• WILCOXON RANK BASED PRINCIPAL COMPONENT ANALYSIS
• Efficient R-estimation of principal and common principal components
• Rank-based testing for semiparametric VAR models: a measure transportation approach
• Likelihood ratio tests for principal components
• Semiparametric partial common principal component analysis for covariance matrices
• Distribution and quantile functions, ranks and signs in dimension \(d\): a measure transportation approach
• On the asymptotic behavior of the leading eigenvector of Tyler's shape estimator under weak identifiability
• A conversation with Marc Hallin
• On testing the equality of latent roots of scatter matrices under ellipticity
• Performance evaluation of likelihood-ratio tests for assessing similarity of the covariance matrices of two multivariate normal populations
• Power enhancement for dimension detection of Gaussian signals
• Testing axial symmetry by means of directional regression quantiles
• Testing symmetry around a subspace
• Statistical inference for principal components of spiked covariance matrices
• A note on the regularity of optimal-transport-based center-outward distribution and quantile functions
• Semiparametric error-correction models for cointegration with trends: pseudo-Gaussian and optimal rank-based tests of the cointegration rank
• Optimal rank-based tests for homogeneity of scatter
• Testing for principal component directions under weak identifiability
• ECA: High-Dimensional Elliptical Component Analysis in Non-Gaussian Distributions
• Scale-invariant sparse PCA on high-dimensional meta-elliptical data
• On the efficiency of some rank-based test for the homogeneity of concentrations
• Efficient ANOVA for directional data
• Sign tests for weak principal directions
• Optimal rank-based tests against first-order superdiagonal bilinear dependence
• On weighted multivariate sign functions
• Optimal rank-based tests for common principal components

This page was built for publication: Optimal rank-based testing for principal components

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q620547)