Edgeworth Expansion for the Kernel Quantile Estimator Maesono, Y. en_US Penev, Spiridon en_US 2021-11-25T13:40:55Z 2021-11-25T13:40:55Z 2009 en_US
dc.description.abstract Using the kernel estimator of the pth quantile of a distribution brings about an improvement in comparison to the sample quantile estimator. The size and order of this improvement is revealed when studying the Edgeworth expansion of the kernel estimator. Using one more term beyond the normal approximation significantly improves the accuracy for small to moderate samples. The investigation is non- standard since the influence function of the resulting L-statistic explicitly depends on the sample size. We obtain the expansion, justify its validity and demonstrate the numerical gains in using it. en_US
dc.identifier.issn 0020-3157 en_US
dc.language English
dc.language.iso EN en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri en_US
dc.source Legacy MARC en_US
dc.title Edgeworth Expansion for the Kernel Quantile Estimator en_US
dc.type Journal Article en
dcterms.accessRights metadata only access
dspace.entity.type Publication en_US
unsw.identifier.doiPublisher en_US
unsw.relation.faculty Science
unsw.relation.ispartofjournal Annals of the Institute of Statistical Mathematics en_US
unsw.relation.ispartofvolume Published Online: 4 June 2009 en_US
unsw.relation.originalPublicationAffiliation Maesono, Y. en_US
unsw.relation.originalPublicationAffiliation Penev, Spiridon, Mathematics & Statistics, Faculty of Science, UNSW en_US School of Mathematics & Statistics *
Resource type