Bandwidth choice for nonparametric classification

Simple item page
dc.creatorHall, Peter
dc.creatorKang, Kee-Hoon
dc.date2005-04-25
dc.date.accessioned2026-07-07T08:06:51Z
dc.date.available2026-07-07T08:06:51Z
dc.descriptionIt is shown that, for kernel-based classification with univariate distributions and two populations, optimal bandwidth choice has a dichotomous character. If the two densities cross at just one point, where their curvatures have the same signs, then minimum Bayes risk is achieved using bandwidths which are an order of magnitude larger than those which minimize pointwise estimation error. On the other hand, if the curvature signs are different, or if there are multiple crossing points, then bandwidths of conventional size are generally appropriate. The range of different modes of behavior is narrower in multivariate settings. There, the optimal size of bandwidth is generally the same as that which is appropriate for pointwise density estimation. These properties motivate empirical rules for bandwidth choice.
dc.descriptionPublished at http://dx.doi.org/10.1214/009053604000000959 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/math/0504511
dc.identifierhttp://arxiv.org/abs/math/0504511
dc.identifierAnnals of Statistics 2005, Vol. 33, No. 1, 284-306
dc.identifierdoi:10.1214/009053604000000959
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/130748
dc.subjectStatistics Theory
dc.subject62H30, 62C12 (Primary) 62G07. (Secondary)
dc.titleBandwidth choice for nonparametric classification
dc.typetext

Files

Collections

arXiv