User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Analysis of bivariate tail dependence using extreme value copulas: an application to the SOA medical large claims database

Primary tabs

Cebrian Ana, Carmen [Universidad de Zaragoza] Denuit, Michel [UCL] Lambert, Philippe [UCL]

The aim of this work is to analyze the dependence structure between losses and ALAE’s relating to large claims using extreme value copulas. A procedure to select and estimate the copula based on a parametric estimation of the dependence function is proposed. An application to the evaluation of reinsurance premiums is performed in group medical insurance. This work clearly enhances the relevance of the copula-based approach to model claim amounts and their associated ALAE’s.

Document type Article de périodique (Journal article) – Article de recherche
Publication date 2003
Language Anglais
Journal information "Belgian Actuarial Bulletin" - Vol. 3, p. 33-41 (2003)
Peer reviewed yes
issn 1784-5742
e-issn 1784-5750
Publication status Publié
Affiliation Louvain School of Management
Keywords extreme value copulas ; bivariate extreme value distributions ; dependence function ; excess-of-loss reinsurance premiums
Links
Bibliographic reference Cebrian Ana, Carmen ; Denuit, Michel ; Lambert, Philippe. Analysis of bivariate tail dependence using extreme value copulas: an application to the SOA medical large claims database. In: Belgian Actuarial Bulletin, Vol. 3, p. 33-41 (2003)
Permanent URL http://hdl.handle.net/2078/17222