File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Assessing local influence in canonical correlation analysis

TitleAssessing local influence in canonical correlation analysis
Authors
KeywordsCanonical Correlation Analysis
Diagnostics
Local Influence
Perturbation
Tests Of Independence
Issue Date1998
Citation
Annals Of The Institute Of Statistical Mathematics, 1998, v. 50 n. 4, p. 755-772 How to Cite?
AbstractThe first order local influence approach is adopted in this paper to assess the local influence of observations to canonical correlation coefficients, canonical vectors and several relevant test statistics in canonical correlation analysis. This approach can detect different aspects of influence due to different perturbation schemes. In this paper, we consider two different kinds, namely, the additive perturbation scheme and the case-weights perturbation scheme. It is found that, under the additive perturbation scheme, the influence analysis of any canonical correlation coefficient can be simplified to just observing two predicted residuals. To do the influence analysis for canonical vectors, a scale invariant norm is proposed. Furthermore, by choosing proper perturbation scales on different variables, we can compare the different influential effects of perturbations on different variables under the additive perturbation scheme. An example is presented to illustrate the effectiveness of the first order local influence approach.
Persistent Identifierhttp://hdl.handle.net/10722/172478
ISSN
2015 Impact Factor: 0.768
2015 SCImago Journal Rankings: 0.931
References

 

DC FieldValueLanguage
dc.contributor.authorGu, Hen_US
dc.contributor.authorFung, WKen_US
dc.date.accessioned2012-10-30T06:22:43Z-
dc.date.available2012-10-30T06:22:43Z-
dc.date.issued1998en_US
dc.identifier.citationAnnals Of The Institute Of Statistical Mathematics, 1998, v. 50 n. 4, p. 755-772en_US
dc.identifier.issn0020-3157en_US
dc.identifier.urihttp://hdl.handle.net/10722/172478-
dc.description.abstractThe first order local influence approach is adopted in this paper to assess the local influence of observations to canonical correlation coefficients, canonical vectors and several relevant test statistics in canonical correlation analysis. This approach can detect different aspects of influence due to different perturbation schemes. In this paper, we consider two different kinds, namely, the additive perturbation scheme and the case-weights perturbation scheme. It is found that, under the additive perturbation scheme, the influence analysis of any canonical correlation coefficient can be simplified to just observing two predicted residuals. To do the influence analysis for canonical vectors, a scale invariant norm is proposed. Furthermore, by choosing proper perturbation scales on different variables, we can compare the different influential effects of perturbations on different variables under the additive perturbation scheme. An example is presented to illustrate the effectiveness of the first order local influence approach.en_US
dc.languageengen_US
dc.relation.ispartofAnnals of the Institute of Statistical Mathematicsen_US
dc.subjectCanonical Correlation Analysisen_US
dc.subjectDiagnosticsen_US
dc.subjectLocal Influenceen_US
dc.subjectPerturbationen_US
dc.subjectTests Of Independenceen_US
dc.titleAssessing local influence in canonical correlation analysisen_US
dc.typeArticleen_US
dc.identifier.emailFung, WK: wingfung@hku.hken_US
dc.identifier.authorityFung, WK=rp00696en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-7844219847en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-7844219847&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume50en_US
dc.identifier.issue4en_US
dc.identifier.spage755en_US
dc.identifier.epage772en_US
dc.publisher.placeGermanyen_US
dc.identifier.scopusauthoridGu, H=55225103300en_US
dc.identifier.scopusauthoridFung, WK=13310399400en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats