Publication:
Evaluation of outlier detection method performance in symmetric multivariate distributions

dc.contributor.authorUzabacı, Ender
dc.contributor.authorErcan, İlker
dc.contributor.authorAlpu, Özlem
dc.contributor.buuauthorUZABACI, ENDER
dc.contributor.buuauthorERCAN, İLKER
dc.contributor.departmentBursa Uludağ Üniversitesi/Veteriner Fakültesi/Biyoistatistik Anabilim Dalı.
dc.contributor.departmentBursa Uludağ Üniversitesi/Tıp Fakültesi/Biyoistatistik Anabilim Dalı.
dc.contributor.orcid0000-0002-9634-0055
dc.contributor.orcid0000-0002-2382-290X
dc.contributor.researcheridJPL-5273-2023
dc.contributor.researcheridABF-2367-2020
dc.date.accessioned2024-07-04T07:02:47Z
dc.date.available2024-07-04T07:02:47Z
dc.date.issued2020-02-01
dc.description.abstractDetermining outliers is more complicated in multivariate data sets than it is in univariate cases. The aim of this study is to evaluate the blocked adaptive computationally efficient outlier nominators (BACON) algorithm, the fast minimum covariance determinant (FAST-MCD) method, and the robust Mahalanobis distance (RM) method in multivariate data sets. For this purpose, outlier detection methods were compared for multivariate normal, Laplace, and Cauchy distributions with different sample sizes and numbers of variables. False-negative and false-positive ratios were used to evaluate the methods' performance. The results of this work indicate that the performance of these methods varies according to the distribution type.
dc.identifier.doi10.1080/03610918.2018.1487068
dc.identifier.endpage531
dc.identifier.issn0361-0918
dc.identifier.issue2
dc.identifier.startpage516
dc.identifier.urihttps://doi.org/10.1080/03610918.2018.1487068
dc.identifier.urihttps://www.tandfonline.com/doi/full/10.1080/03610918.2018.1487068
dc.identifier.urihttps://hdl.handle.net/11452/42864
dc.identifier.volume49
dc.identifier.wos000506465200015
dc.indexed.wosWOS.SCI
dc.language.isoen
dc.publisherTaylor & Francis
dc.relation.journalCommunications in Statistics-Simulation and Computation
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectRobust statistics
dc.subjectMultiple outliers
dc.subjectIdentification
dc.subjectBacon
dc.subjectAlgorithm
dc.subjectMahalanobis distance
dc.subjectMultivariate data
dc.subjectOutlier
dc.subjectRobust statistics
dc.subjectMathematics
dc.titleEvaluation of outlier detection method performance in symmetric multivariate distributions
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublication415edb5b-1ae0-491a-bd6a-97c2d1a6ec1e
relation.isAuthorOfPublication50e4dfdb-25cd-43af-94c9-464881669605
relation.isAuthorOfPublication.latestForDiscovery415edb5b-1ae0-491a-bd6a-97c2d1a6ec1e

Files

Collections