Testing Kronecker product covariance matrices for high-dimensional matrix-variate data

Summary The Kronecker product covariance structure provides an efficient way to model the inter-correlations of matrix-variate data. In this paper, we propose test statistics for the Kronecker product covariance matrix based on linear spectral statistics of renormalized sample covariance matrices. A...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biometrika 2023-09, Vol.110 (3), p.799-814
Hauptverfasser: Yu, Long, Xie, Jiahui, Zhou, Wang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 814
container_issue 3
container_start_page 799
container_title Biometrika
container_volume 110
creator Yu, Long
Xie, Jiahui
Zhou, Wang
description Summary The Kronecker product covariance structure provides an efficient way to model the inter-correlations of matrix-variate data. In this paper, we propose test statistics for the Kronecker product covariance matrix based on linear spectral statistics of renormalized sample covariance matrices. A central limit theorem is proved for the linear spectral statistics, with explicit formulas for the mean and covariance functions, thereby filling a gap in the literature. We then show theoretically that the proposed test statistics have well-controlled size and high power. We further propose a bootstrap resampling algorithm to approximate the limiting distributions of the associated linear spectral statistics. Consistency of the bootstrap procedure is guaranteed under mild conditions. The proposed test procedure is also applicable to the Kronecker product covariance model with additional random noise. In our simulations, the empirical sizes of the proposed test procedure and its bootstrapped version are close to the corresponding theoretical values, while the power converges to $1$ quickly as the dimension and sample size increase.
doi_str_mv 10.1093/biomet/asac063
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3049129624</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/biomet/asac063</oup_id><sourcerecordid>3049129624</sourcerecordid><originalsourceid>FETCH-LOGICAL-c301t-e93cefe096c1272f93694ae715183a95bf1d859fcc4114ddd0f401ec092738cd3</originalsourceid><addsrcrecordid>eNqFkL1PwzAQxS0EEqWwMkdiYnBrx45Tj6jiS1RiKayWa59blyYutoPgvycl3ZlOp_u903sPoWtKJpRINl350ECe6qQNEewEjSgXHLOKklM0IoQIzDjn5-gipe1hFZUYofclpOzbdfESQwvmA2Kxj8F2JhcmfOnodWugaHSO3kAqXIjFxq832PoG2uRDq3fD9Rv_0RkKq7O-RGdO7xJcHecYvT3cL-dPePH6-Dy_W2DDCM0YJDPggEhhaFmXTjIhuYaaVnTGtKxWjtpZJZ0xnFJurSWOEwqGyLJmM2PZGN0Mf3vTn10fRW1DF3tTSTHCJS2lKHlPTQbKxJBSBKf20Tc6_ihK1KE7NXSnjt31gttBELr9f-wvpqFzyQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3049129624</pqid></control><display><type>article</type><title>Testing Kronecker product covariance matrices for high-dimensional matrix-variate data</title><source>Oxford University Press Journals All Titles (1996-Current)</source><creator>Yu, Long ; Xie, Jiahui ; Zhou, Wang</creator><creatorcontrib>Yu, Long ; Xie, Jiahui ; Zhou, Wang</creatorcontrib><description>Summary The Kronecker product covariance structure provides an efficient way to model the inter-correlations of matrix-variate data. In this paper, we propose test statistics for the Kronecker product covariance matrix based on linear spectral statistics of renormalized sample covariance matrices. A central limit theorem is proved for the linear spectral statistics, with explicit formulas for the mean and covariance functions, thereby filling a gap in the literature. We then show theoretically that the proposed test statistics have well-controlled size and high power. We further propose a bootstrap resampling algorithm to approximate the limiting distributions of the associated linear spectral statistics. Consistency of the bootstrap procedure is guaranteed under mild conditions. The proposed test procedure is also applicable to the Kronecker product covariance model with additional random noise. In our simulations, the empirical sizes of the proposed test procedure and its bootstrapped version are close to the corresponding theoretical values, while the power converges to $1$ quickly as the dimension and sample size increase.</description><identifier>ISSN: 0006-3444</identifier><identifier>EISSN: 1464-3510</identifier><identifier>DOI: 10.1093/biomet/asac063</identifier><language>eng</language><publisher>Oxford: Oxford University Press</publisher><subject>Algorithms ; Covariance matrix ; Mathematical analysis ; Random noise ; Resampling ; Statistical analysis ; Statistical tests ; Statistics ; Test procedures</subject><ispartof>Biometrika, 2023-09, Vol.110 (3), p.799-814</ispartof><rights>The Author(s) 2022. Published by Oxford University Press on behalf of the Biometrika Trust. All rights reserved. For permissions, please email: journals.permissions@oup.com 2022</rights><rights>The Author(s) 2022. Published by Oxford University Press on behalf of the Biometrika Trust. All rights reserved. For permissions, please email: journals.permissions@oup.com</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c301t-e93cefe096c1272f93694ae715183a95bf1d859fcc4114ddd0f401ec092738cd3</citedby><cites>FETCH-LOGICAL-c301t-e93cefe096c1272f93694ae715183a95bf1d859fcc4114ddd0f401ec092738cd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,1584,27924,27925</link.rule.ids></links><search><creatorcontrib>Yu, Long</creatorcontrib><creatorcontrib>Xie, Jiahui</creatorcontrib><creatorcontrib>Zhou, Wang</creatorcontrib><title>Testing Kronecker product covariance matrices for high-dimensional matrix-variate data</title><title>Biometrika</title><description>Summary The Kronecker product covariance structure provides an efficient way to model the inter-correlations of matrix-variate data. In this paper, we propose test statistics for the Kronecker product covariance matrix based on linear spectral statistics of renormalized sample covariance matrices. A central limit theorem is proved for the linear spectral statistics, with explicit formulas for the mean and covariance functions, thereby filling a gap in the literature. We then show theoretically that the proposed test statistics have well-controlled size and high power. We further propose a bootstrap resampling algorithm to approximate the limiting distributions of the associated linear spectral statistics. Consistency of the bootstrap procedure is guaranteed under mild conditions. The proposed test procedure is also applicable to the Kronecker product covariance model with additional random noise. In our simulations, the empirical sizes of the proposed test procedure and its bootstrapped version are close to the corresponding theoretical values, while the power converges to $1$ quickly as the dimension and sample size increase.</description><subject>Algorithms</subject><subject>Covariance matrix</subject><subject>Mathematical analysis</subject><subject>Random noise</subject><subject>Resampling</subject><subject>Statistical analysis</subject><subject>Statistical tests</subject><subject>Statistics</subject><subject>Test procedures</subject><issn>0006-3444</issn><issn>1464-3510</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqFkL1PwzAQxS0EEqWwMkdiYnBrx45Tj6jiS1RiKayWa59blyYutoPgvycl3ZlOp_u903sPoWtKJpRINl350ECe6qQNEewEjSgXHLOKklM0IoQIzDjn5-gipe1hFZUYofclpOzbdfESQwvmA2Kxj8F2JhcmfOnodWugaHSO3kAqXIjFxq832PoG2uRDq3fD9Rv_0RkKq7O-RGdO7xJcHecYvT3cL-dPePH6-Dy_W2DDCM0YJDPggEhhaFmXTjIhuYaaVnTGtKxWjtpZJZ0xnFJurSWOEwqGyLJmM2PZGN0Mf3vTn10fRW1DF3tTSTHCJS2lKHlPTQbKxJBSBKf20Tc6_ihK1KE7NXSnjt31gttBELr9f-wvpqFzyQ</recordid><startdate>20230901</startdate><enddate>20230901</enddate><creator>Yu, Long</creator><creator>Xie, Jiahui</creator><creator>Zhou, Wang</creator><general>Oxford University Press</general><general>Oxford Publishing Limited (England)</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope></search><sort><creationdate>20230901</creationdate><title>Testing Kronecker product covariance matrices for high-dimensional matrix-variate data</title><author>Yu, Long ; Xie, Jiahui ; Zhou, Wang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c301t-e93cefe096c1272f93694ae715183a95bf1d859fcc4114ddd0f401ec092738cd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Covariance matrix</topic><topic>Mathematical analysis</topic><topic>Random noise</topic><topic>Resampling</topic><topic>Statistical analysis</topic><topic>Statistical tests</topic><topic>Statistics</topic><topic>Test procedures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yu, Long</creatorcontrib><creatorcontrib>Xie, Jiahui</creatorcontrib><creatorcontrib>Zhou, Wang</creatorcontrib><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Biometrika</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Long</au><au>Xie, Jiahui</au><au>Zhou, Wang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Testing Kronecker product covariance matrices for high-dimensional matrix-variate data</atitle><jtitle>Biometrika</jtitle><date>2023-09-01</date><risdate>2023</risdate><volume>110</volume><issue>3</issue><spage>799</spage><epage>814</epage><pages>799-814</pages><issn>0006-3444</issn><eissn>1464-3510</eissn><abstract>Summary The Kronecker product covariance structure provides an efficient way to model the inter-correlations of matrix-variate data. In this paper, we propose test statistics for the Kronecker product covariance matrix based on linear spectral statistics of renormalized sample covariance matrices. A central limit theorem is proved for the linear spectral statistics, with explicit formulas for the mean and covariance functions, thereby filling a gap in the literature. We then show theoretically that the proposed test statistics have well-controlled size and high power. We further propose a bootstrap resampling algorithm to approximate the limiting distributions of the associated linear spectral statistics. Consistency of the bootstrap procedure is guaranteed under mild conditions. The proposed test procedure is also applicable to the Kronecker product covariance model with additional random noise. In our simulations, the empirical sizes of the proposed test procedure and its bootstrapped version are close to the corresponding theoretical values, while the power converges to $1$ quickly as the dimension and sample size increase.</abstract><cop>Oxford</cop><pub>Oxford University Press</pub><doi>10.1093/biomet/asac063</doi><tpages>16</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0006-3444
ispartof Biometrika, 2023-09, Vol.110 (3), p.799-814
issn 0006-3444
1464-3510
language eng
recordid cdi_proquest_journals_3049129624
source Oxford University Press Journals All Titles (1996-Current)
subjects Algorithms
Covariance matrix
Mathematical analysis
Random noise
Resampling
Statistical analysis
Statistical tests
Statistics
Test procedures
title Testing Kronecker product covariance matrices for high-dimensional matrix-variate data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T12%3A47%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Testing%20Kronecker%20product%20covariance%20matrices%20for%20high-dimensional%20matrix-variate%20data&rft.jtitle=Biometrika&rft.au=Yu,%20Long&rft.date=2023-09-01&rft.volume=110&rft.issue=3&rft.spage=799&rft.epage=814&rft.pages=799-814&rft.issn=0006-3444&rft.eissn=1464-3510&rft_id=info:doi/10.1093/biomet/asac063&rft_dat=%3Cproquest_cross%3E3049129624%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3049129624&rft_id=info:pmid/&rft_oup_id=10.1093/biomet/asac063&rfr_iscdi=true