Publication:
Cluster identification using projections

Simple item page
dc.affiliation.dptoUC3M. Departamento de Estadísticaes
dc.contributor.authorPeña, Daniel
dc.contributor.authorPrieto, Francisco J.
dc.date.accessioned2012-10-02T18:43:26Z
dc.date.available2012-10-02T18:43:26Z
dc.date.issued2001-12
dc.description.abstractThis artiele describes a procedure to identify elusters in multivariate data using information obtained from the univariate projections of the sample data onto certain directions. The directions are chosen as those that minimize and maximize the kurtosis coefficlent of the projected data. It is shown that, under certain conditions, these directions provide the largest separatlOn for the dlfferent clusters. The projected univariate data are used to group the observations according to the values of the gaps or spacings between consecutive-ordered observations. These groupings are then combined over all projection directions. The behavior of the method is tested on several examples, and compared to k-means, MCLUST, and the procedure proposed by Jones and Sibson in 1987. The proposed algonthm is iterative, affine equivariant, flexible, robust to outliers, fast to implement, and seems to work well in practice
dc.description.sponsorshipThis research was supported by Spanish grant BEC2000-0167
dc.description.statusPublicado
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationJournal of the American Statistical Association, 2001, v. 96, n. 456, p. 1433-1445
dc.identifier.issn0162-1459
dc.identifier.publicationfirstpage1433
dc.identifier.publicationissue456
dc.identifier.publicationlastpage1445
dc.identifier.publicationtitleJournal of the American Statistical Association
dc.identifier.publicationvolume96
dc.identifier.urihttps://hdl.handle.net/10016/15524
dc.language.isoeng
dc.publisherAmerican Statistical Association
dc.relation.publisherversionhttp://www.jstor.org/stable/3085911
dc.rights© American Statistical Association
dc.rights.accessRightsopen access
dc.subject.ecienciaEstadística
dc.subject.otherClassification
dc.subject.otherKurtosis
dc.subject.otherMultivariate analysis
dc.subject.otherRobustness
dc.subject.otherSpacings
dc.titleCluster identification using projections
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cluster_prieto_JASA_2001_ps.pdf
Size:
1.47 MB
Format:
Adobe Portable Document Format
Download
Collections
DES - Artículos de Revistas