Confidence regions for high quantiles of a heavy tailed distribution

Simple item page
dc.creatorPeng, Liang
dc.creatorQi, Yongcheng
dc.date2006-11-09
dc.date.accessioned2026-07-07T08:08:23Z
dc.date.available2026-07-07T08:08:23Z
dc.descriptionEstimating high quantiles plays an important role in the context of risk management. This involves extrapolation of an unknown distribution function. In this paper we propose three methods, namely, the normal approximation method, the likelihood ratio method and the data tilting method, to construct confidence regions for high quantiles of a heavy tailed distribution. A simulation study prefers the data tilting method.
dc.descriptionPublished at http://dx.doi.org/10.1214/009053606000000416 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/0611278
dc.identifierhttp://arxiv.org/abs/math/0611278
dc.identifierAnnals of Statistics 2006, Vol. 34, No. 4, 1964-1986
dc.identifierdoi:10.1214/009053606000000416
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/131246
dc.subjectStatistics Theory
dc.subject62G32 (Primary) 62G02 (Secondary)
dc.titleConfidence regions for high quantiles of a heavy tailed distribution
dc.typetext

Files

Collections

arXiv