Limit theorem associated with Wishart matrices with application to hypothesis testing for common principal components

DOI10.1016/J.JMVA.2021.104822zbMATH Open1476.62129arXiv2005.01316OpenAlexW3197867634MaRDI QIDQ2237828FDOQ2237828

Authors: Koji Tsukuda, Shun Matsuura 

Publication date: 28 October 2021

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

Abstract: This study derives a new property of the Wishart distribution when the degree-of-freedom and the size of the matrix parameter of the distribution grow simultaneoulsy. Particularly, the asymptotic normality of the product of four independent Wishart matrices is shown under a high dimensional asymptotic regime. As an application of the result, a statistical test procedure for the common principal components hypothesis is proposed. For this problem, the proposed test statistic is asymptotically normal under the null hypothesis. In addition, the proposed test statistic diverges to positive infinity in probability under the alternative hypothesis.

Full work available at URL: https://arxiv.org/abs/2005.01316

Recommendations

• A test of the hypothesis of partial common principal components
• A class of asymptotic tests for principal component vectors
• Asymptotic normality of high-dimensional Wilks'\(\lambda\) statistics
• Hypothesis testing for high-dimensional covariance matrices
• Some new properties of Wishart distribution

zbMATH Keywords

central limit theoremWishart distributionhigh-dimensionasymptotic testcommon principal components model

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Asymptotic properties of parametric tests (62F05) Central limit and other weak theorems (60F05)

Cites Work

• Two sample tests for high-dimensional covariance matrices
• Asymptotic theory for common principal component analysis
• Title not available (Why is that?)
• Spectral models for covariance matrices
• A test for the equality of covariance matrices when the dimension is large relative to the sample sizes
• Title not available (Why is that?)
• Title not available (Why is that?)
• Tests for high-dimensional covariance matrices
• Tests for covariance matrices in high dimension with less sample size
• High-dimensional testing for proportional covariance matrices
• Testing the equality of several covariance matrices with fewer observations than the dimension
• Two-stage procedures for high-dimensional data
• A new test for the proportionality of two large-dimensional covariance matrices
• Testing block-diagonal covariance structure for high-dimensional data under non-normality
• Optimal rank-based tests for common principal components
• Hypothesis tests for high-dimensional covariance structures
• Robust tests for the common principal components model
• Testing for common principal components under heterokurticity
• Testing for independence of high-dimensional variables: \(\rho V\)-coefficient based approach
• Testing proportionality of two large-dimensional covariance matrices
• Two-sample tests for high-dimension, strongly spiked eigenvalue models
• Equality tests of high-dimensional covariance matrices under the strongly spiked eigenvalue model
• A test of sphericity for high-dimensional data and its application for detection of divergently spiked noise
• Test for equality of generalized variance in high-dimensional and large sample settings

Cited In (2)

• Integral transform methods in goodness-of-fit testing. II: The Wishart distributions
• High-dimensional asymptotic behavior of the difference between the log-determinants of two Wishart matrices

This page was built for publication: Limit theorem associated with Wishart matrices with application to hypothesis testing for common principal components

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2237828)