Kernel estimation of extreme risk measures for all domains of attraction - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2016

Kernel estimation of extreme risk measures for all domains of attraction

Abstract

Variance are classical risk measures. In statistical terms, the Value-at-risk is the upper α-quantile of the loss distribution where α ∈ (0, 1) is the confidence level. Here, we focus on the properties of these risk measures for extreme losses (where α ↓ 0 is no longer fixed). To assign probabilities to extreme losses we assume that the distribution satisfies a von-Mises condi- tion which allows us to work in the general setting, whether the extreme- value index is positive, negative or zero i.e. for all domains of attraction. We also consider these risk measures in the presence of a covariate. The main goal of this communication is to propose estimators of the above risk measures for all domains of attraction, for extreme losses, and to include a covariate in the estimation. The estimation method thus combines non- parametric kernel methods with extreme-value statistics. The asymptotic distribution of our estimators is established and their finite sample behavior is illustrated on simulated data and on a real data set of daily rainfall.
CIRM.pdf (1.51 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01312846 , version 1 (09-05-2016)

Identifiers

  • HAL Id : hal-01312846 , version 1

Cite

Jonathan El Methni, Stéphane Girard, Laurent Gardes. Kernel estimation of extreme risk measures for all domains of attraction. Extremes, Copulas and Actuarial Sciences, Feb 2016, Marseille, France. ⟨hal-01312846⟩
288 View
26 Download

Share

More