ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS

A randomly generated Latin hypercube design (LHD) can be quite structured: the variables may be highly correlated or the design may not have good space-filling properties. There are procedures for finding good LHDs by minimizing the pairwise correlations or by maximizing the inter-site distances. In...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Statistica Sinica 2008-01, Vol.18 (1), p.171-186
Hauptverfasser:	Joseph, V. Roshan, Hung, Ying
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Correlations Experiment design Integers Kriging Mathematical sequences Maximin Modeling Objective functions Performance metrics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	186
container_issue	1
container_start_page	171
container_title	Statistica Sinica
container_volume	18
creator	Joseph, V. Roshan Hung, Ying
description	A randomly generated Latin hypercube design (LHD) can be quite structured: the variables may be highly correlated or the design may not have good space-filling properties. There are procedures for finding good LHDs by minimizing the pairwise correlations or by maximizing the inter-site distances. In this article we show that these two criteria need not be in close agreement. We propose a multi-objective optimization approach to find good LHDs by combining correlation and distance performance measures. We also propose a new exchange algorithm for efficiently generating such designs. Several examples are presented to show that the new algorithm is fast, and that the optimal designs are good in terms of both the correlation and distance criteria.
format	Article
fullrecord	<record><control><sourceid>jstor</sourceid><recordid>TN_cdi_jstor_primary_24308251</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>24308251</jstor_id><sourcerecordid>24308251</sourcerecordid><originalsourceid>FETCH-LOGICAL-j177t-8573bcc6434a78369ab188e457504ebe48cf9fb1374801002c6e4a705192b9b33</originalsourceid><addsrcrecordid>eNotTssKgkAUHaKgqD4haB0Id7wzzszSzFTwEalQq3BkhKIotE1_30BtzjmL8xqRGVXKcyQHMbYaqHCAAZ-S5TBcNYACTiXgjGyKYxUXUZH7qZP5pyRL8nXqVxbj8yE8BvU2XO_CMonyckEmXXMfzPLPc1LvwyqInbSIksDmb1SIt90UqNvWY8gaIdFTjaZSGsYFB2a0YbLtVKcpCiaBAritZ6zTHlKuVhpxTla_3tvwfvaXV399NP3n4jIE6XKKX3stN40</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS</title><source>JSTOR</source><source>EZB Electronic Journals Library</source><creator>Joseph, V. Roshan ; Hung, Ying</creator><creatorcontrib>Joseph, V. Roshan ; Hung, Ying</creatorcontrib><description>A randomly generated Latin hypercube design (LHD) can be quite structured: the variables may be highly correlated or the design may not have good space-filling properties. There are procedures for finding good LHDs by minimizing the pairwise correlations or by maximizing the inter-site distances. In this article we show that these two criteria need not be in close agreement. We propose a multi-objective optimization approach to find good LHDs by combining correlation and distance performance measures. We also propose a new exchange algorithm for efficiently generating such designs. Several examples are presented to show that the new algorithm is fast, and that the optimal designs are good in terms of both the correlation and distance criteria.</description><identifier>ISSN: 1017-0405</identifier><identifier>EISSN: 1996-8507</identifier><language>eng</language><publisher>Institute of Statistical Science, Academia Sinica and International Chinese Statistical Association</publisher><subject>Algorithms ; Correlations ; Experiment design ; Integers ; Kriging ; Mathematical sequences ; Maximin ; Modeling ; Objective functions ; Performance metrics</subject><ispartof>Statistica Sinica, 2008-01, Vol.18 (1), p.171-186</ispartof><rights>2008 STATISTICA SINICA</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/24308251$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/24308251$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>315,781,785,804,833,58022,58026,58255,58259</link.rule.ids></links><search><creatorcontrib>Joseph, V. Roshan</creatorcontrib><creatorcontrib>Hung, Ying</creatorcontrib><title>ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS</title><title>Statistica Sinica</title><description>A randomly generated Latin hypercube design (LHD) can be quite structured: the variables may be highly correlated or the design may not have good space-filling properties. There are procedures for finding good LHDs by minimizing the pairwise correlations or by maximizing the inter-site distances. In this article we show that these two criteria need not be in close agreement. We propose a multi-objective optimization approach to find good LHDs by combining correlation and distance performance measures. We also propose a new exchange algorithm for efficiently generating such designs. Several examples are presented to show that the new algorithm is fast, and that the optimal designs are good in terms of both the correlation and distance criteria.</description><subject>Algorithms</subject><subject>Correlations</subject><subject>Experiment design</subject><subject>Integers</subject><subject>Kriging</subject><subject>Mathematical sequences</subject><subject>Maximin</subject><subject>Modeling</subject><subject>Objective functions</subject><subject>Performance metrics</subject><issn>1017-0405</issn><issn>1996-8507</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid/><recordid>eNotTssKgkAUHaKgqD4haB0Id7wzzszSzFTwEalQq3BkhKIotE1_30BtzjmL8xqRGVXKcyQHMbYaqHCAAZ-S5TBcNYACTiXgjGyKYxUXUZH7qZP5pyRL8nXqVxbj8yE8BvU2XO_CMonyckEmXXMfzPLPc1LvwyqInbSIksDmb1SIt90UqNvWY8gaIdFTjaZSGsYFB2a0YbLtVKcpCiaBAritZ6zTHlKuVhpxTla_3tvwfvaXV399NP3n4jIE6XKKX3stN40</recordid><startdate>20080101</startdate><enddate>20080101</enddate><creator>Joseph, V. Roshan</creator><creator>Hung, Ying</creator><general>Institute of Statistical Science, Academia Sinica and International Chinese Statistical Association</general><scope/></search><sort><creationdate>20080101</creationdate><title>ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS</title><author>Joseph, V. Roshan ; Hung, Ying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-j177t-8573bcc6434a78369ab188e457504ebe48cf9fb1374801002c6e4a705192b9b33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Algorithms</topic><topic>Correlations</topic><topic>Experiment design</topic><topic>Integers</topic><topic>Kriging</topic><topic>Mathematical sequences</topic><topic>Maximin</topic><topic>Modeling</topic><topic>Objective functions</topic><topic>Performance metrics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Joseph, V. Roshan</creatorcontrib><creatorcontrib>Hung, Ying</creatorcontrib><jtitle>Statistica Sinica</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Joseph, V. Roshan</au><au>Hung, Ying</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS</atitle><jtitle>Statistica Sinica</jtitle><date>2008-01-01</date><risdate>2008</risdate><volume>18</volume><issue>1</issue><spage>171</spage><epage>186</epage><pages>171-186</pages><issn>1017-0405</issn><eissn>1996-8507</eissn><abstract>A randomly generated Latin hypercube design (LHD) can be quite structured: the variables may be highly correlated or the design may not have good space-filling properties. There are procedures for finding good LHDs by minimizing the pairwise correlations or by maximizing the inter-site distances. In this article we show that these two criteria need not be in close agreement. We propose a multi-objective optimization approach to find good LHDs by combining correlation and distance performance measures. We also propose a new exchange algorithm for efficiently generating such designs. Several examples are presented to show that the new algorithm is fast, and that the optimal designs are good in terms of both the correlation and distance criteria.</abstract><pub>Institute of Statistical Science, Academia Sinica and International Chinese Statistical Association</pub><tpages>16</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 1017-0405
ispartof	Statistica Sinica, 2008-01, Vol.18 (1), p.171-186
issn	1017-0405 1996-8507
language	eng
recordid	cdi_jstor_primary_24308251
source	JSTOR; EZB Electronic Journals Library
subjects	Algorithms Correlations Experiment design Integers Kriging Mathematical sequences Maximin Modeling Objective functions Performance metrics
title	ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T16%3A04%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ORTHOGONAL-MAXIMIN%20LATIN%20HYPERCUBE%20DESIGNS&rft.jtitle=Statistica%20Sinica&rft.au=Joseph,%20V.%20Roshan&rft.date=2008-01-01&rft.volume=18&rft.issue=1&rft.spage=171&rft.epage=186&rft.pages=171-186&rft.issn=1017-0405&rft.eissn=1996-8507&rft_id=info:doi/&rft_dat=%3Cjstor%3E24308251%3C/jstor%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_jstor_id=24308251&rfr_iscdi=true