On Rohlf′s Method for the Detection of Outliers in Multivariate Data

Caroni, C; Prescott, P

dc.contributor.author	Caroni, C	en
dc.contributor.author	Prescott, P	en
dc.date.accessioned	2014-03-01T01:11:18Z
dc.date.available	2014-03-01T01:11:18Z
dc.date.issued	1995	en
dc.identifier.issn	0047-259X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/11599
dc.subject	OUTLIER TESTS	en
dc.subject	MULTIVARIATE OUTLIERS	en
dc.subject	ROHLFS TEST	en
dc.subject	GAP TESTS	en
dc.subject	GAMMA DISTRIBUTION	en
dc.subject.classification	Statistics & Probability	en
dc.subject.other	MULTIPLE OUTLIERS	en
dc.subject.other	POINTS	en
dc.title	On Rohlf′s Method for the Detection of Outliers in Multivariate Data	en
heal.type	journalArticle	en
heal.identifier.primary	10.1006/jmva.1995.1015	en
heal.identifier.secondary	http://dx.doi.org/10.1006/jmva.1995.1015	en
heal.language	English	en
heal.publicationDate	1995	en
heal.abstract	Rohlf (1975, Biometrics31, 93-101) proposed a method of detecting outliers in multivariate data by testing the largest edge of the minimum spanning tree. It is shown here that tests against the gamma distribution are extremely liberal. Furthermore, results depend on the correlation structure of the data if Euclidean distances are used. While the use of generalized distances might avoid this difficulty, the construction of the robust estimates required to carry out the test with generalized distances provides in itself information on outliers which leaves Rohlf′s procedure superfluous. It is concluded that Rohlf′s method does not provide a useful formal test. © 1995 Academic Press. All rights reserved.	en
heal.publisher	ACADEMIC PRESS INC JNL-COMP SUBSCRIPTIONS	en
heal.journalName	Journal of Multivariate Analysis	en
dc.identifier.doi	10.1006/jmva.1995.1015	en
dc.identifier.isi	ISI:A1995QH97600006	en
dc.identifier.volume	52	en
dc.identifier.issue	2	en
dc.identifier.spage	295	en
dc.identifier.epage	307	en