Loading…
Roy's largest root test under rank-one alternatives
Roy's largest root is a common test statistic in multivariate analysis, statistical signal processing and allied fields. Despite its ubiquity, provision of accurate and tractable approximations to its distribution under the alternative has been a longstanding open problem. Assuming Gaussian obs...
Saved in:
| Published in: | Biometrika 2017-03, Vol.104 (1), p.181-193 |
|---|---|
| Main Authors: | , |
| Format: | Article |
| Language: | English |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3 |
| container_end_page | 193 |
| container_issue | 1 |
| container_start_page | 181 |
| container_title | Biometrika |
| container_volume | 104 |
| creator | JOHNSTONE, I. M. NADLER, B. |
| description | Roy's largest root is a common test statistic in multivariate analysis, statistical signal processing and allied fields. Despite its ubiquity, provision of accurate and tractable approximations to its distribution under the alternative has been a longstanding open problem. Assuming Gaussian observations and a rank-one alternative, or concentrated noncentrality, we derive simple yet accurate approximations for the most common low-dimensional settings. These include signal detection in noise, multiple response regression, multivariate analysis of variance and canonical correlation analysis. A small-noise perturbation approach, perhaps underused in statistics, leads to simple combinations of standard univariate distributions, such as central and noncentral χ2 and F. Our results allow approximate power and sample size calculations for Roy's test for rank-one effects, which is precisely where it is most powerful. |
| doi_str_mv | 10.1093/biomet/asw060 |
| format | article |
| fullrecord | <record><control><sourceid>jstor_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5793689</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>26363651</jstor_id><sourcerecordid>26363651</sourcerecordid><originalsourceid>FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3</originalsourceid><addsrcrecordid>eNpVkMtLw0AQxhdRbH0cPSq56SV2Nvu-CFJ8QUGQ3pdtsq2pabbubir9701IrcocZob58c3Mh9AFhlsMioxmpVvZODLhCzgcoCGmnKaEYThEQwDgKaGUDtBJCMuu5Ywfo0GmKAEgMETkzW2vQ1IZv7AhJt65mMSuaurC-sSb-iN1tU1MFa2vTSw3Npyho7mpgj3f5VM0fXyYjp_TyevTy_h-kuYUVEwFMxhLIwRlWAosMQOTG8qMmsNMMZwXWcEpA6CZZAJooYyQlMsuMlGQU3TXy66b2coWua2jN5Ve-3Jl_FY7U-r_k7p81wu30UwowqVqBW52At59Nu1TelWG3FaVqa1rgs4AMAWSSWjRtEdz70Lwdr5fg0F3PuveZ9373PJXf2_b0z_GtsBlDyxDdP53zkkbDJNvuzuDog</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2001403280</pqid></control><display><type>article</type><title>Roy's largest root test under rank-one alternatives</title><source>JSTOR Archival Journals and Primary Sources Collection</source><source>Oxford Journals Online</source><creator>JOHNSTONE, I. M. ; NADLER, B.</creator><creatorcontrib>JOHNSTONE, I. M. ; NADLER, B.</creatorcontrib><description>Roy's largest root is a common test statistic in multivariate analysis, statistical signal processing and allied fields. Despite its ubiquity, provision of accurate and tractable approximations to its distribution under the alternative has been a longstanding open problem. Assuming Gaussian observations and a rank-one alternative, or concentrated noncentrality, we derive simple yet accurate approximations for the most common low-dimensional settings. These include signal detection in noise, multiple response regression, multivariate analysis of variance and canonical correlation analysis. A small-noise perturbation approach, perhaps underused in statistics, leads to simple combinations of standard univariate distributions, such as central and noncentral χ2 and F. Our results allow approximate power and sample size calculations for Roy's test for rank-one effects, which is precisely where it is most powerful.</description><identifier>ISSN: 0006-3444</identifier><identifier>EISSN: 1464-3510</identifier><identifier>DOI: 10.1093/biomet/asw060</identifier><identifier>PMID: 29430030</identifier><language>eng</language><publisher>England: Biometrika Trust</publisher><ispartof>Biometrika, 2017-03, Vol.104 (1), p.181-193</ispartof><rights>2017 Biometrika Trust</rights><rights>2017 Biometrika Trust 2017</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3</citedby><cites>FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/26363651$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/26363651$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>230,314,776,780,881,27903,27904,58216,58449</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29430030$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>JOHNSTONE, I. M.</creatorcontrib><creatorcontrib>NADLER, B.</creatorcontrib><title>Roy's largest root test under rank-one alternatives</title><title>Biometrika</title><addtitle>Biometrika</addtitle><description>Roy's largest root is a common test statistic in multivariate analysis, statistical signal processing and allied fields. Despite its ubiquity, provision of accurate and tractable approximations to its distribution under the alternative has been a longstanding open problem. Assuming Gaussian observations and a rank-one alternative, or concentrated noncentrality, we derive simple yet accurate approximations for the most common low-dimensional settings. These include signal detection in noise, multiple response regression, multivariate analysis of variance and canonical correlation analysis. A small-noise perturbation approach, perhaps underused in statistics, leads to simple combinations of standard univariate distributions, such as central and noncentral χ2 and F. Our results allow approximate power and sample size calculations for Roy's test for rank-one effects, which is precisely where it is most powerful.</description><issn>0006-3444</issn><issn>1464-3510</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNpVkMtLw0AQxhdRbH0cPSq56SV2Nvu-CFJ8QUGQ3pdtsq2pabbubir9701IrcocZob58c3Mh9AFhlsMioxmpVvZODLhCzgcoCGmnKaEYThEQwDgKaGUDtBJCMuu5Ywfo0GmKAEgMETkzW2vQ1IZv7AhJt65mMSuaurC-sSb-iN1tU1MFa2vTSw3Npyho7mpgj3f5VM0fXyYjp_TyevTy_h-kuYUVEwFMxhLIwRlWAosMQOTG8qMmsNMMZwXWcEpA6CZZAJooYyQlMsuMlGQU3TXy66b2coWua2jN5Ve-3Jl_FY7U-r_k7p81wu30UwowqVqBW52At59Nu1TelWG3FaVqa1rgs4AMAWSSWjRtEdz70Lwdr5fg0F3PuveZ9373PJXf2_b0z_GtsBlDyxDdP53zkkbDJNvuzuDog</recordid><startdate>20170301</startdate><enddate>20170301</enddate><creator>JOHNSTONE, I. M.</creator><creator>NADLER, B.</creator><general>Biometrika Trust</general><general>Oxford University Press</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20170301</creationdate><title>Roy's largest root test under rank-one alternatives</title><author>JOHNSTONE, I. M. ; NADLER, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>JOHNSTONE, I. M.</creatorcontrib><creatorcontrib>NADLER, B.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Biometrika</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>JOHNSTONE, I. M.</au><au>NADLER, B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Roy's largest root test under rank-one alternatives</atitle><jtitle>Biometrika</jtitle><addtitle>Biometrika</addtitle><date>2017-03-01</date><risdate>2017</risdate><volume>104</volume><issue>1</issue><spage>181</spage><epage>193</epage><pages>181-193</pages><issn>0006-3444</issn><eissn>1464-3510</eissn><abstract>Roy's largest root is a common test statistic in multivariate analysis, statistical signal processing and allied fields. Despite its ubiquity, provision of accurate and tractable approximations to its distribution under the alternative has been a longstanding open problem. Assuming Gaussian observations and a rank-one alternative, or concentrated noncentrality, we derive simple yet accurate approximations for the most common low-dimensional settings. These include signal detection in noise, multiple response regression, multivariate analysis of variance and canonical correlation analysis. A small-noise perturbation approach, perhaps underused in statistics, leads to simple combinations of standard univariate distributions, such as central and noncentral χ2 and F. Our results allow approximate power and sample size calculations for Roy's test for rank-one effects, which is precisely where it is most powerful.</abstract><cop>England</cop><pub>Biometrika Trust</pub><pmid>29430030</pmid><doi>10.1093/biomet/asw060</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0006-3444 |
| ispartof | Biometrika, 2017-03, Vol.104 (1), p.181-193 |
| issn | 0006-3444 1464-3510 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5793689 |
| source | JSTOR Archival Journals and Primary Sources Collection; Oxford Journals Online |
| title | Roy's largest root test under rank-one alternatives |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T04%3A18%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Roy's%20largest%20root%20test%20under%20rank-one%20alternatives&rft.jtitle=Biometrika&rft.au=JOHNSTONE,%20I.%20M.&rft.date=2017-03-01&rft.volume=104&rft.issue=1&rft.spage=181&rft.epage=193&rft.pages=181-193&rft.issn=0006-3444&rft.eissn=1464-3510&rft_id=info:doi/10.1093/biomet/asw060&rft_dat=%3Cjstor_pubme%3E26363651%3C/jstor_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c409t-75a118a774518718150aca45a9f0b951cd2d645004285704d9a78468686827d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2001403280&rft_id=info:pmid/29430030&rft_jstor_id=26363651&rfr_iscdi=true |