Approximation and estimation of very small probabilities of multivariate extreme events

DOI10.1007/S10687-016-0252-6MaRDI QIDQ347151zbMATH OpenOpenAlexFDO

Authors Cees de Valk

Publication date 30 November 2016

Published in Extremes (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1503.00489

zbMATH Keywords

multivariate extremeshidden regular variationlarge deviation principlegeneralised Weibull tail limitlog-GW tail limitresidual tail dependence

Mathematics Subject Classification ID

Large deviations (60F10) Extreme value theory; extremal stochastic processes (60G70) Statistics of extreme values; tail inference (62G32)

Abstract: This article discusses modelling of the tail of a multivariate distribution function by means of a large deviation principle (LDP), and its application to the estimation of the probability of a multivariate extreme event from a sample of n iid random vectors, with the probability bounded by powers of sample size with exponents below -1. One way to view classical tail limits is as limits of probability ratios. In contrast, the tail LDP provides asymptotic bounds or limits for log-probability ratios. After standardising the marginals to standard exponential, dependence is represented by a homogeneous rate function. Furthermore, the tail LDP can be extended to represent both dependence and marginals, the latter implying marginal log-GW tail limits. A connection is established between the tail LDP and residual tail dependence (or hidden regular variation) and a recent extension of it. Under a smoothness assumption, they are implied by the tail LDP. Based on the tail LDP, a simple estimator for very small probabilities of extreme events is formulated. It avoids estimation of the rate function by making use of its homogeneity. Strong consistency in the sense of convergence of log-probability ratios is proven. Simulations and an application illustrate the difference between the classical approach and the LDP-based approach.

Recommendations

• Bivariate tail estimation: dependence in asymptotic independence
• A new representation for multivariate tail probabilities
• On the estimation of extreme tail probabilities
• scientific article; zbMATH DE number 5787344
• Likelihood estimators for multivariate extremes

Cites work

• scientific article; zbMATH DE number 3820920 (Why is no real title available?)
• scientific article; zbMATH DE number 3824949 (Why is no real title available?)
• scientific article; zbMATH DE number 4030574 (Why is no real title available?)
• scientific article; zbMATH DE number 409721 (Why is no real title available?)
• scientific article; zbMATH DE number 469373 (Why is no real title available?)
• scientific article; zbMATH DE number 1085999 (Why is no real title available?)
• scientific article; zbMATH DE number 1158743 (Why is no real title available?)
• scientific article; zbMATH DE number 4000257 (Why is no real title available?)
• A Conditional Approach for Multivariate Extreme Values (with Discussion)
• A new representation for multivariate tail probabilities
• Approximation of high quantiles from intermediate quantiles
• Asymptotic normality of extreme value estimators on \(C[0,1]\)
• Bivariate tail estimation: dependence in asymptotic independence
• Comparison of Approaches for Estimating the Probability of Coastal Flooding
• Concomitant tail behaviour for extremes
• Estimating failure probabilities
• Estimating the probability of a rare event
• Estimation of the coefficient of tail dependence in bivariate extremes
• Estimation of the conditional distribution of a multivariate variable given that one of its components is large: additional constraints for the Heffernan and Tawn model
• Extreme value theory. An introduction.
• Hidden regular variation and the rank transform
• Hidden regular variation, second order regular variation and asymptotic independence
• Limit laws for random vectors with an extreme component
• Limit theorems for the ratio of the empirical distribution function to the true distribution function
• Linear bounds on the empirical distribution function
• On convergence toward an extreme value distribution in \(C[0,1]\)
• On the estimation of the Weibull tail coefficient
• Statistical Methods for Multivariate Extremes: An Application to Structural Design
• Statistical inference using extreme order statistics
• Statistics for near independence in multivariate extreme values
• Statistics of Multivariate Extremes
• The generalized Pareto process; with a view towards application and simulation

Cited in

(12)

• Nonparametric estimation of multivariate tail probabilities and tail dependence coefficients
• On dealing with the unknown population minimum in parametric inference
• On tests to distinguish distribution tails invariant with respect to the scale parameter
• Approximation rates for multivariate exceedances
• Linking representations for multivariate extremes via a limit set
• Estimation of extreme quantiles from heavy-tailed distributions with neural networks
• Samples with a limit shape, multivariate extremes, and risk
• Exceedance-based nonlinear regression of tail dependence
• Sub-asymptotic motivation for new conditional multivariate extreme models
• Asymptotic behavior of the extrapolation error associated with the estimation of extreme quantiles
• Estimating the probability of a rare event via elliptical copulas
• Extremiles: A New Perspective on Asymmetric Least Squares

This page was built for publication: Approximation and estimation of very small probabilities of multivariate extreme events

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q347151)