A comparison of different procedures for principal component analysis in the presence of outliers

Basit Öğe Kaydı
dc.authoridAtakan, Cemal/0000-0001-6943-1675
dc.authoridalkan, nesrin/0000-0003-1452-4780
dc.contributor.authorAlkan, B. Baris
dc.contributor.authorAtakan, Cemal
dc.contributor.authorAlkan, Nesrin
dc.date.accessioned2025-03-23T19:35:19Z
dc.date.available2025-03-23T19:35:19Z
dc.date.issued2015
dc.departmentSinop Üniversitesi
dc.description.abstractPrincipal component analysis (PCA) is a popular technique that is useful for dimensionality reduction but it is affected by the presence of outliers. The outlier sensitivity of classical PCA (CPCA) has caused the development of new approaches. Effects of using estimates obtained by expectation-maximization - EM and multiple imputation - MI instead of outliers were examined on the artificial and a real data set. Furthermore, robust PCA based on minimum covariance determinant (MCD), PCA based on estimates obtained by EM instead of outliers and PCA based on estimates obtained by MI instead of outliers were compared with the results of CPCA. In this study, we tried to show the effects of using estimates obtained by MI and EM instead of outliers, depending on the ratio of outliers in data set. Finally, when the ratio of outliers exceeds 20%, we suggest the use of estimates obtained by MI and EM instead of outliers as an alternative approach.
dc.identifier.doi10.1080/02664763.2015.1005063
dc.identifier.endpage1722
dc.identifier.issn0266-4763
dc.identifier.issn1360-0532
dc.identifier.issue8
dc.identifier.scopus2-s2.0-84929944879
dc.identifier.scopusqualityQ1
dc.identifier.startpage1716
dc.identifier.urihttps://doi.org/10.1080/02664763.2015.1005063
dc.identifier.urihttps://hdl.handle.net/11486/5840
dc.identifier.volume42
dc.identifier.wosWOS:000355107100008
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherTaylor & Francis Ltd
dc.relation.ispartofJournal of Applied Statistics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250323
dc.subjectmultiple imputation
dc.subjectoutliers
dc.subjectmissing value
dc.subjectexpectation-maximization
dc.subjectprincipal component analysis
dc.titleA comparison of different procedures for principal component analysis in the presence of outliers
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu