Wilks' outlier test in more than one multivariate sample

Caroni, C

dc.contributor.author	Caroni, C	en
dc.date.accessioned	2014-03-01T01:14:16Z
dc.date.available	2014-03-01T01:14:16Z
dc.date.issued	1998	en
dc.identifier.issn	0361-0918	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12970
dc.subject	MANOVA	en
dc.subject	Multivariate normal	en
dc.subject	Outliers	en
dc.subject	Robustness	en
dc.subject	Wilks' test	en
dc.subject.classification	Statistics & Probability	en
dc.title	Wilks' outlier test in more than one multivariate sample	en
heal.type	journalArticle	en
heal.identifier.primary	10.1080/03610919808813466	en
heal.identifier.secondary	http://dx.doi.org/10.1080/03610919808813466	en
heal.language	English	en
heal.publicationDate	1998	en
heal.abstract	Wilks' test for a single outlier in a multivariate normal sample is extended to the case of samples from different subpopulations with common covariance matrix, a situation arising in MANOVA, for example. Simulation results show that the size of the test is acceptably robust to moderate heterogeneity in covariances (25-50% difference in total variation), especially if sample sizes are small (below 20 per group). However covariance heterogeneity leads to a drastic loss of power, unless this heterogeneity is concentrated in one dimension and the outlier appears in a different dimension. It is concluded that the extended test should be used with caution since it will often be difficult to establish whether these conditions hold.	en
heal.publisher	MARCEL DEKKER INC	en
heal.journalName	Communications in Statistics Part B: Simulation and Computation	en
dc.identifier.doi	10.1080/03610919808813466	en
dc.identifier.isi	ISI:000072492100006	en
dc.identifier.volume	27	en
dc.identifier.issue	1	en
dc.identifier.spage	79	en
dc.identifier.epage	94	en