Copulas based on Marshall–Olkin machinery

Fabrizio Durante 1 Stéphane Girard 2 Gildas Mazo 3
1 Free University of Bozen-Bolzano
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 UCL - Université Catholique de Louvain
Abstract : We present a general construction principle for copulas that is inspired by the celebrated Marshall–Olkin exponential model. From this general construction method we derive special sub–classes of copulas that could be useful in different situations and recall their main properties. Moreover, we discuss possible estimation strategy for the proposed copulas. The presented results are expected to be useful in the construction of stochastic models for lifetimes (e.g. in reliability theory) or in credit risk models.
Type de document :
Chapitre d'ouvrage
U. Cherubini et al. Marshall-Olkin Distributions. Advances in Theory and Applications, 141, Springer, pp.15--31, 2015, Springer Proceedings in Mathematics and Statistics
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01153150
Contributeur : Stephane Girard <>
Soumis le : mardi 19 mai 2015 - 10:59:52
Dernière modification le : mercredi 14 décembre 2016 - 01:07:23
Document(s) archivé(s) le : mardi 15 septembre 2015 - 06:09:13

Fichier

Durante_Girard_Mazo_Final_Revi...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01153150, version 1

Collections

INSMI | LJK | UGA | INRIA | LJK_PS | LJK_PS_MISTIS

Citation

Fabrizio Durante, Stéphane Girard, Gildas Mazo. Copulas based on Marshall–Olkin machinery. U. Cherubini et al. Marshall-Olkin Distributions. Advances in Theory and Applications, 141, Springer, pp.15--31, 2015, Springer Proceedings in Mathematics and Statistics. <hal-01153150>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

289

Téléchargements du document

157

Contact

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