Improved estimators of extreme Wang distortion risk measures for very heavy-tailed distributions - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Econometrics and Statistics Année : 2018

Improved estimators of extreme Wang distortion risk measures for very heavy-tailed distributions

Résumé

A general way to study the extremes of a random variable is to consider the family of its Wang distortion risk measures. This class of risk measures encompasses several popular indicators such as the classical quantile/Value-at-Risk, the Tail-Value-at-Risk and the recently introduced Conditional Tail Moments, among others. A couple of very recent studies have focused on the estimation of extreme analogues of such quantities. In this paper, we consider trimmed and winsorised versions of the empirical counterparts of extreme Wang distortion risk measures. We analyse their asymptotic properties, and we show that we can construct bias-corrected trimmed or winsorised estimators of extreme Wang distortion risk measures who appear to perform overall better than their standard empirical counterparts in practice when the underlying distribution has a very heavy right tail. We also showcase our technique on a set of real fire insurance data.
Fichier principal
Vignette du fichier
ExtremeRiskTruncated_revised_full_HAL.pdf (877.03 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01406342 , version 1 (01-12-2016)
hal-01406342 , version 2 (07-03-2017)

Identifiants

  • HAL Id : hal-01406342 , version 2

Citer

Jonathan El Methni, Gilles Stupfler. Improved estimators of extreme Wang distortion risk measures for very heavy-tailed distributions. Econometrics and Statistics , 2018, 6, pp.129-148. ⟨hal-01406342v2⟩
309 Consultations
258 Téléchargements

Partager

Gmail Facebook X LinkedIn More