On the relative approximation error of extreme quantiles by the block maxima method

Clément Albert 1 Anne Dutfoy 2 Stéphane Girard 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
2 EDF R&D MRI - Management des Risques Industriels
Abstract : This study takes place in the context of extreme quantiles estimation by the block maxima method. We investigate the behaviour of the relative approximation error of a quantile estimator dedicated to the Gumbel maximum domain of attraction. Our work is based on a regular variation assumption on the first derivative of the logarithm of the inverse cumulative hazard rate function, introduced by de Valk (2016) [Approximation of high quantiles from intermediate quantiles. Extremes 19(4), 661-686]. We give necessary and sufficient conditions under which the relative approximation error of the extreme quantile computed with the block maxima method converges to zero. We also provide a first order approximation of the relative approximation error when the latter converges towards zero. Our results are illustrated on simulated data.
Keywords : Extreme quantiles estimation relative approximation error asymptotic properties regular variation
Type de document :
Communication dans un congrès
10th International Conference on Extreme Value Analysis, Jun 2017, Delft, Netherlands. 10th International Conference on Extreme Value Analysis, 2017
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01571047
Contributeur : Stephane Girard <>
Soumis le : mardi 1 août 2017 - 14:45:19
Dernière modification le : mercredi 11 avril 2018 - 01:59:13

Fichier

albert-c.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01571047, version 1

Collections

INSMI | LJK | INRIA2017 | INRIA | UGA | LJK_PS | LJK_PS_MISTIS

Citation

Clément Albert, Anne Dutfoy, Stéphane Girard. On the relative approximation error of extreme quantiles by the block maxima method. 10th International Conference on Extreme Value Analysis, Jun 2017, Delft, Netherlands. 10th International Conference on Extreme Value Analysis, 2017. 〈hal-01571047〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

221

Téléchargements de fichiers

51

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD