Optimal rank-based tests for homogeneity of scatter

Simple item page
dc.creatorHallin, Marc
dc.creatorPaindaveine, Davy
dc.date2008-06-18
dc.date.accessioned2026-07-07T12:19:36Z
dc.date.available2026-07-07T12:19:36Z
dc.descriptionWe propose a class of locally and asymptotically optimal tests, based on multivariate ranks and signs for the homogeneity of scatter matrices in $m$ elliptical populations. Contrary to the existing parametric procedures, these tests remain valid without any moment assumptions, and thus are perfectly robust against heavy-tailed distributions (validity robustness). Nevertheless, they reach semiparametric efficiency bounds at correctly specified elliptical densities and maintain high powers under all (efficiency robustness). In particular, their normal-score version outperforms traditional Gaussian likelihood ratio tests and their pseudo-Gaussian robustifications under a very broad range of non-Gaussian densities including, for instance, all multivariate Student and power-exponential distributions.
dc.descriptionPublished in at http://dx.doi.org/10.1214/07-AOS508 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0806.2963
dc.identifierhttp://arxiv.org/abs/0806.2963
dc.identifierAnnals of Statistics 2008, Vol. 36, No. 3, 1261-1298
dc.identifierdoi:10.1214/07-AOS508
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212812
dc.subjectStatistics Theory
dc.subject62M15, 62G35 (Primary)
dc.titleOptimal rank-based tests for homogeneity of scatter
dc.typetext

Files

Collections

arXiv