Modeling of censored bivariate extremal events
Détails
Télécharger: BIB_C3FB10FFC52E.P001.pdf (787.88 [Ko])
Etat: Public
Version: de l'auteur⸱e
Etat: Public
Version: de l'auteur⸱e
ID Serval
serval:BIB_C3FB10FFC52E
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Institution
Titre
Modeling of censored bivariate extremal events
Périodique
Journal of the Korean Statistical Society
ISSN
1226-3192 (Print)
Statut éditorial
Publié
Date de publication
2014
Peer-reviewed
Oui
Volume
43
Numéro
3
Pages
323-338
Langue
anglais
Résumé
In this paper we consider the estimation of the coefficient of tail dependence and of small tail probability under a bivariate randomly censoring mechanism. A new class of generalized moment estimators of the coefficient of tail dependence and the estimator of small tail probability are proposed, respectively. Under the bivariate Hall-type conditions, the asymptotic distributions of these estimators are established. Monte Carlo simulations are performed and the new estimators are applied to an insurance data-set.
Mots-clé
Randomly censoring, Coefficient of tail dependence, Large claims, Small tail probability, Concomitant order statistics, Bivariate Hall-class
Web of science
Création de la notice
20/10/2013 17:33
Dernière modification de la notice
20/08/2019 16:39