File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Article: Use of the Sign Test for the Median in the Presence of Ties

TitleUse of the Sign Test for the Median in the Presence of Ties
Authors
KeywordsLikelihood ratio test
Paired samples
Power
Type I error
Issue Date2003
PublisherAmerican Statistical Association. The Journal's web site is located at http://www.amstat.org/publications/tas/index.cfm?fuseaction=main
Citation
American Statistician, 2003, v. 57 n. 4, p. 237-240 How to Cite?
AbstractThe sign test was developed to examine the median difference of paired samples. Ignorance of ties - that is, zero differences - in the sign test can substantially inflate the Type I error rate. A uniformly most powerful test has been developed to test for the symmetry of the positive and negative differences but little attention has been given about inferences concerning the median difference when ties are abundant. This article examines a simple modified sign test which can be implemented in most computer packages and a likelihood ratio test.
Persistent Identifierhttp://hdl.handle.net/10722/87558
ISSN
2015 Impact Factor: 1.215
2015 SCImago Journal Rankings: 0.732
References

 

DC FieldValueLanguage
dc.contributor.authorFong, DYTen_HK
dc.contributor.authorKwan, CWen_HK
dc.contributor.authorLam, KFen_HK
dc.contributor.authorLam, KSLen_HK
dc.date.accessioned2010-09-06T09:31:24Z-
dc.date.available2010-09-06T09:31:24Z-
dc.date.issued2003en_HK
dc.identifier.citationAmerican Statistician, 2003, v. 57 n. 4, p. 237-240en_HK
dc.identifier.issn0003-1305en_HK
dc.identifier.urihttp://hdl.handle.net/10722/87558-
dc.description.abstractThe sign test was developed to examine the median difference of paired samples. Ignorance of ties - that is, zero differences - in the sign test can substantially inflate the Type I error rate. A uniformly most powerful test has been developed to test for the symmetry of the positive and negative differences but little attention has been given about inferences concerning the median difference when ties are abundant. This article examines a simple modified sign test which can be implemented in most computer packages and a likelihood ratio test.en_HK
dc.languageengen_HK
dc.publisherAmerican Statistical Association. The Journal's web site is located at http://www.amstat.org/publications/tas/index.cfm?fuseaction=mainen_HK
dc.relation.ispartofAmerican Statisticianen_HK
dc.subjectLikelihood ratio testen_HK
dc.subjectPaired samplesen_HK
dc.subjectPoweren_HK
dc.subjectType I erroren_HK
dc.titleUse of the Sign Test for the Median in the Presence of Tiesen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0003-1305&volume=57&issue=4&spage=237&epage=240&date=2003&atitle=Use+of+the+Sign+Test+for+the+Median+in+the+Presence+of+Tiesen_HK
dc.identifier.emailFong, DYT: dytfong@hku.hken_HK
dc.identifier.emailLam, KF: hrntlkf@hkucc.hku.hken_HK
dc.identifier.emailLam, KSL: ksllam@hku.hken_HK
dc.identifier.authorityFong, DYT=rp00253en_HK
dc.identifier.authorityLam, KF=rp00718en_HK
dc.identifier.authorityLam, KSL=rp00343en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-0242458479en_HK
dc.identifier.hkuros85382en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0242458479&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume57en_HK
dc.identifier.issue4en_HK
dc.identifier.spage237en_HK
dc.identifier.epage240en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridFong, DYT=35261710300en_HK
dc.identifier.scopusauthoridKwan, CW=7201421220en_HK
dc.identifier.scopusauthoridLam, KF=8948421200en_HK
dc.identifier.scopusauthoridLam, KSL=8082870600en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats