ASYMPTOTIC MULTIVARIATE EXPECTILES

Véronique Maume-Deschamps (1) , Didier Rullière (2) , Khalil Said (3)

1 PSPM - Probabilités, statistique, physique mathématique
2 SAF - Laboratoire de Sciences Actuarielle et Financière
3 Ecole d'Actuariat

In [16], a new family of vector-valued risk measures called multivariate expectiles is introduced. In this paper, we focus on the asymptotic behavior of these measures in a multivariate regular variations context. For models with equivalent tails, we propose an estimator of these multivariate asymptotic expectiles, in the Fréchet attraction domain case, with asymptotic independence, or in the comonotonic case.

Mots clés: Risk measures; tail dependence functions; multivariate expectiles; extreme values; regular variations

Domaines: Gestion des risques [q-fin.RM]; Applications [stat.AP]

Véronique Maume-Deschamps, Didier Rullière, Khalil Said. ASYMPTOTIC MULTIVARIATE EXPECTILES. 2018. ⟨hal-01509963v2⟩