Tail-dependence, exceedance sets, and metric embeddings

DOI10.1007/S10687-023-00471-ZMaRDI QIDQ6144816zbMATH OpenOpenAlexFDO

Authors Anja Janssen, Sebastian Neblung, Stilian Stoev

Publication date 8 January 2024

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/2212.01044

zbMATH Keywords

Bernoulli compatibilityexceedance setsline metricsmax-stable vectorsmetric embeddingmultivariate regular variationNP completenessrealization problem for TD matricestail-dependence coefficientstail-dependence matrixTawn-Molchanov models

Mathematics Subject Classification ID

General theory of distance geometry (51K05) Probability distributions: general theory (60E05) Extreme value theory; extremal stochastic processes (60G70) Analysis of algorithms and problem complexity (68Q25) Metric embeddings as related to computational problems and algorithms (68R12)

Abstract: There are many ways of measuring and modeling tail-dependence in random vectors: from the general framework of multivariate regular variation and the flexible class of max-stable vectors down to simple and concise summary measures like the matrix of bivariate tail-dependence coefficients. This paper starts by providing a review of existing results from a unifying perspective, which highlights connections between extreme value theory and the theory of cuts and metrics. Our approach leads to some new findings in both areas with some applications to current topics in risk management. We begin by using the framework of multivariate regular variation to show that extremal coefficients, or equivalently, the higher-order tail-dependence coefficients of a random vector can simply be understood in terms of random exceedance sets, which allows us to extend the notion of Bernoulli compatibility. In the special but important case of bi-variate tail-dependence, we establish a correspondence between tail-dependence matrices and $L^1$- and $el{l}_1$-embeddable finite metric spaces via the spectral distance, which is a metric on the space of jointly $1$-Fr'{e}chet random variables. Namely, the coefficients of the cut-decomposition of the spectral distance and of the Tawn-Molchanov max-stable model realizing the corresponding bi-variate extremal dependence coincide. We show that line metrics are rigid and if the spectral distance corresponds to a line metric, the higher order tail-dependence is determined by the bi-variate tail-dependence matrix. Finally, the correspondence between $el{l}_1$-embeddable metric spaces and tail-dependence matrices allows us to revisit the realizability problem, i.e. checking whether a given matrix is a valid tail-dependence matrix. We confirm a conjecture of Shyamalkumar & Tao (2020) that this problem is NP-complete.

Recommendations

• On tail dependence matrices. The realization problem for parametric families
• Bernoulli and tail-dependence compatibility
• Decompositions of dependence for high-dimensional extremes
• Tail dependence between order statistics
• Tail dependence from a distributional point of view

Cites work

• A dependence measure for multivariate and spatial extreme values: Properties and inference
• A note on vague convergence of measures
• A spectral representation for max-stable processes
• An exceptional max-stable process fully parameterized by its extremal coefficients
• An introduction to statistical modeling of extreme values
• Basic properties and prediction of max-ARMA processes
• Bernoulli and tail-dependence compatibility
• Bounds for the sum of dependent risks having overlapping marginals
• Correlation polytopes: Their geometry and complexity
• Dependence measures for extreme value analyses
• Distributionally robust inference for extreme value-at-risk
• Estimating the tail-dependence coefficient: properties and pitfalls
• Extremal stochastic integrals: a parallel between max-stable processes and \(\alpha\)-stable processes
• Geometry of cuts and metrics
• Heavy tailed time series
• Heavy-Tail Phenomena
• Homogeneous mappings of regularly varying vectors
• scientific article; zbMATH DE number 4030574 (Why is no real title available?)
• scientific article; zbMATH DE number 193577 (Why is no real title available?)
• Inequalities for the extremal coefficients of multivariate extreme value distributions
• Max-stable random sup-measures with comonotonic tail dependence
• Membership testing for Bernoulli and tail-dependence matrices
• On tail dependence matrices. The realization problem for parametric families
• Prediction of stationary max-stable processes
• Regular variation for measures on metric spaces
• Statistics of Extremes
• Tail correlation functions of max-stable processes
• The cut cone,L1 embeddability, complexity, and multicommodity flows
• The realization problem for tail correlation functions
• Theory of Random Sets

Cited in

(4)

• Shift-invariant homogeneous classes of random fields
• On the optimal prediction of extreme events in heavy-tailed time series with applications to solar flare forecasting
• Mathematics, statistics, and geometry of extreme events in high dimensions. Abstracts from the workshop held August 19--23, 2024
• Extremal correlation coefficient for functional data

This page was built for publication: Tail-dependence, exceedance sets, and metric embeddings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144816)