File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Optimal bootstrap sample size in construction of percentile confidence bounds

TitleOptimal bootstrap sample size in construction of percentile confidence bounds
Authors
KeywordsBackwards percentile
Confidence bound
Cornish-Fisher expansion
Coverage error
Double bootstrap
Edgeworth expansion
Hybrid percentile
m/n bootstrap
Smooth function model
Issue Date2001
PublisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/SJOS
Citation
Scandinavian Journal Of Statistics, 2001, v. 28 n. 1, p. 225-239 How to Cite?
AbstractIn traditional bootstrap applications the size of a bootstrap sample equals the parent sample size, n say. Recent studies have shown that using a bootstrap sample size different from n may sometimes provide a more satisfactory solution. In this paper we apply the latter approach to correct for coverage error in construction of bootstrap confidence bounds. We show that the coverage error of a bootstrap percentile method confidence bound, which is of order O(n-1/2) typically, can be reduced to O(n-1) by use of an optimal bootstrap sample size. A simulation study is conducted to illustrate our findings, which also suggest that the new method yields intervals of shorter length and greater stability compared to competitors of similar coverage accuracy.
Persistent Identifierhttp://hdl.handle.net/10722/82921
ISSN
2015 Impact Factor: 0.908
2015 SCImago Journal Rankings: 1.362
References

 

DC FieldValueLanguage
dc.contributor.authorChung, KHen_HK
dc.contributor.authorLee, SMSen_HK
dc.date.accessioned2010-09-06T08:34:54Z-
dc.date.available2010-09-06T08:34:54Z-
dc.date.issued2001en_HK
dc.identifier.citationScandinavian Journal Of Statistics, 2001, v. 28 n. 1, p. 225-239en_HK
dc.identifier.issn0303-6898en_HK
dc.identifier.urihttp://hdl.handle.net/10722/82921-
dc.description.abstractIn traditional bootstrap applications the size of a bootstrap sample equals the parent sample size, n say. Recent studies have shown that using a bootstrap sample size different from n may sometimes provide a more satisfactory solution. In this paper we apply the latter approach to correct for coverage error in construction of bootstrap confidence bounds. We show that the coverage error of a bootstrap percentile method confidence bound, which is of order O(n-1/2) typically, can be reduced to O(n-1) by use of an optimal bootstrap sample size. A simulation study is conducted to illustrate our findings, which also suggest that the new method yields intervals of shorter length and greater stability compared to competitors of similar coverage accuracy.en_HK
dc.languageengen_HK
dc.publisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/SJOSen_HK
dc.relation.ispartofScandinavian Journal of Statisticsen_HK
dc.rightsScandinavian Journal of Statistics. Copyright © Blackwell Publishing Ltd.en_HK
dc.subjectBackwards percentileen_HK
dc.subjectConfidence bounden_HK
dc.subjectCornish-Fisher expansionen_HK
dc.subjectCoverage erroren_HK
dc.subjectDouble bootstrapen_HK
dc.subjectEdgeworth expansionen_HK
dc.subjectHybrid percentileen_HK
dc.subjectm/n bootstrapen_HK
dc.subjectSmooth function modelen_HK
dc.titleOptimal bootstrap sample size in construction of percentile confidence boundsen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0303-6898&volume=28&spage=225&epage=239&date=2001&atitle=Optimal+bootstrap+sample+size+in+construction+of+percentile+confidence+boundsen_HK
dc.identifier.emailLee, SMS: smslee@hku.hken_HK
dc.identifier.authorityLee, SMS=rp00726en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-0035285745en_HK
dc.identifier.hkuros62124en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0035285745&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume28en_HK
dc.identifier.issue1en_HK
dc.identifier.spage225en_HK
dc.identifier.epage239en_HK
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridChung, KH=7404085906en_HK
dc.identifier.scopusauthoridLee, SMS=24280225500en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats