Open Access
November 2008 Estimation of bivariate excess probabilities for elliptical models
Belkacem Abdous, Anne-Laure Fougères, Kilani Ghoudi, Philippe Soulier
Bernoulli 14(4): 1065-1088 (November 2008). DOI: 10.3150/08-BEJ140

Abstract

Let $(X, Y)$ be a random vector whose conditional excess probability $θ(x, y):=P(Y≤y | X>x)$ is of interest. Estimating this kind of probability is a delicate problem as soon as $x$ tends to be large, since the conditioning event becomes an extreme set. Assume that $(X, Y)$ is elliptically distributed, with a rapidly varying radial component. In this paper, three statistical procedures are proposed to estimate $θ(x, y)$ for fixed $x, y$, with $x$ large. They respectively make use of an approximation result of Abdous et al. (cf. Canad. J. Statist. 33 (2005) 317–334, Theorem 1), a new second order refinement of Abdous et al.’s Theorem 1, and a non-approximating method. The estimation of the conditional quantile function $θ(x, ⋅)^←$ for large fixed $x$ is also addressed and these methods are compared via simulations. An illustration in the financial context is also given.

Citation

Download Citation

Belkacem Abdous. Anne-Laure Fougères. Kilani Ghoudi. Philippe Soulier. "Estimation of bivariate excess probabilities for elliptical models." Bernoulli 14 (4) 1065 - 1088, November 2008. https://doi.org/10.3150/08-BEJ140

Information

Published: November 2008
First available in Project Euclid: 6 November 2008

zbMATH: 1155.62042
MathSciNet: MR2543586
Digital Object Identifier: 10.3150/08-BEJ140

Keywords: Asymptotic independence , conditional excess probability , elliptic law , financial contagion , rapidly varying tails

Rights: Copyright © 2008 Bernoulli Society for Mathematical Statistics and Probability

Vol.14 • No. 4 • November 2008
Back to Top