Estimation non-paramétrique des quantiles extrêmes conditionnels

Laurent Gardes 1 Stephane Girard 1 Alexandre Lekina 1
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose a method to estimate quantiles from heavy-tailed distributions when covariate information is available and in the case where the order of the quantile converges to one as the sample size increases. Asymptotic distribution of such an estimator is established in the case where the quantile is in the range of data or near and even beyond the sample. An illustration on simulated data is provided.
Document type :
Conference papers
41èmes Journées de Statistique, May 2009, Bordeaux, France. 2009
Liste complète des métadonnées

https://hal.inria.fr/inria-00386572
Contributor : Conférence Jds2009 <>
Submitted on : Friday, May 22, 2009 - 9:03:01 AM
Last modification on : Tuesday, May 6, 2014 - 12:42:26 PM
Document(s) archivé(s) le : Thursday, June 10, 2010 - 7:34:33 PM

File

p18.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00386572, version 1

Collections

Citation

Laurent Gardes, Stephane Girard, Alexandre Lekina. Estimation non-paramétrique des quantiles extrêmes conditionnels. 41èmes Journées de Statistique, May 2009, Bordeaux, France. 2009. <inria-00386572>

Share

Metrics

Record views

374

Document downloads

116