Asymptotic independence and support detection techniques for heavy-tailed multivariate data

DOI10.1016/J.INSMATHECO.2020.05.002zbMATH Open1448.62074arXiv1904.00917OpenAlexW3029048952MaRDI QIDQ784445FDOQ784445

Sidney I. Resnick, Jaakko Lehtomaa

Publication date: 3 August 2020

Published in: Insurance Mathematics \& Economics (Search for Journal in Brave)

Abstract: One of the central objectives of modern risk management is to find a set of risks where the probability of multiple simultaneous catastrophic events is negligible. That is, risks are taken only when their joint behavior seems sufficiently independent. This paper aims to help to identify asymptotically independent risks by providing additional tools for describing dependence structures of multiple risks when the individual risks can obtain very large values. The study is performed in the setting of multivariate regular variation. We show how asymptotic independence is connected to properties of the support of the angular measure and present an asymptotically consistent estimator of the support. The estimator generalizes to any dimension $Ngeq2$ and requires no prior knowledge of the support. The validity of the support estimate can be rigorously tested under mild assumptions by an asymptotically normal test statistic.

Full work available at URL: https://arxiv.org/abs/1904.00917

Recommendations

• Estimation of extreme risk regions under multivariate regular variation
• Hidden regular variation under full and strong asymptotic dependence
• Estimating asymptotic dependence functionals in multivariate regularly varying models
• Tail risk of multivariate regular variation
• Modeling multiple risks: hidden domain of attraction

zbMATH Keywords

power lawasymptotic independencesupport estimationmultivariate regular variationheavy-tailed data

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Extreme value theory; extremal stochastic processes (60G70) Asymptotic distribution theory in statistics (62E20) Statistics of extreme values; tail inference (62G32) Estimation in multivariate analysis (62H12) Random measures (60G57)

Cites Work

• An introduction to statistical modeling of extreme values
• Power-Law Distributions in Empirical Data
• Dependence Modeling with Copulas
• A plug-in approach to support estimation
• Detection of Abnormal Behavior Via Nonparametric Estimation of the Support
• Title not available (Why is that?)
• Extreme value theory. An introduction.
• An introduction to copulas.
• Title not available (Why is that?)
• Theory of Random Sets
• Title not available (Why is that?)
• Hidden regular variation, second order regular variation and asymptotic independence
• Nonparametric estimation of the spectral measure of an extreme value distribution.
• Heavy-Tail Phenomena
• Maximum empirical likelihood estimation of the spectral measure of an extreme-value distribu\-tion
• Efficient estimation of monotone boundaries
• Estimating the limit distribution of multivariate extremes
• Title not available (Why is that?)
• Set estimation and nonparametric detection.
• Title not available (Why is that?)
• Asymptotic normality in density support estimation
• Estimating the support of a high-dimensional distribution
• Regularly varying measures on metric spaces: hidden regular variation and hidden jumps
• Living on the Multidimensional Edge: Seeking Hidden Risks Using Regular Variation
• Towards estimating extremal serial dependence via the bootstrapped extremogram
• The extremogram: a correlogram for extreme events
• Estimation of the coefficient of tail dependence in bivariate extremes
• Bernoulli and tail-dependence compatibility
• Hidden regular variation and the rank transform
• Power-law distributions in binned empirical data
• Estimating the tail-dependence coefficient: properties and pitfalls
• Risk management: Value at risk and beyond
• Modeling multiple risks: hidden domain of attraction
• Hidden Regular Variation and Detection of Hidden Risks
• Extremal dependence measure and extremogram: the regularly varying case
• The Extremal Dependence Measure and Asymptotic Independence
• Estimating the spectral measure of an extreme value distribution
• Support estimation via moment estimation in presence of noise
• Estimation of a support curve via order statistics
• The class of multivariate max-id copulas with \(\ell_{1}\)-norm symmetric exponent measure
• The extremogram and the cross-extremogram for a bivariate GARCH(1, 1) process
• Hidden regular variation under full and strong asymptotic dependence
• Data mining to investigate the meteorological drivers for extreme ground level ozone events
• Sparse representation of multivariate extremes with applications to anomaly detection
• Models with hidden regular variation: Generation and detection
• On the Hausdorff distance between a convex set and an interior random convex hull
• On the estimation of a star-shaped set
• Limiting behaviour of constrained sums of two variables and the principle of a single big jump

Cited In (3)

• Sparse regular variation
• Discussion of ‘On studying extreme values and systematic risks with nonlinear time series models and tail dependence measures’
• Concentration bounds for the empirical angular measure with statistical learning applications

Uses Software

• R
• quantmod
• ismev
• QRM
• fitdistrplus
• plfit

This page was built for publication: Asymptotic independence and support detection techniques for heavy-tailed multivariate data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q784445)