Extremes of Markov random fields on block graphs: max-stable limits and structured Hüsler-Reiss distributions

DOI10.1007/S10687-023-00467-9MaRDI QIDQ6176326zbMATH OpenOpenAlexFDO

Authors Stefka Asenova, Johan Segers

Publication date 22 August 2023

Published in Extremes (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2112.04847

zbMATH Keywords

block graphconditional independencegraphical modelHüsler-Reiss distributionlatent variableMarkov random fieldmultivariate extremestail dependence

Mathematics Subject Classification ID

Statistical distribution theory (62Exx)

Abstract: We study the joint occurrence of large values of a Markov random field or undirected graphical model associated to a block graph. On such graphs, containing trees as special cases, we aim to generalize recent results for extremes of Markov trees. Every pair of nodes in a block graph is connected by a unique shortest path. These paths are shown to determine the limiting distribution of the properly rescaled random field given that a fixed variable exceeds a high threshold. The latter limit relation implies that the random field is multivariate regularly varying and it determines the max-stable distribution to which component-wise maxima of independent random samples from the field are attracted. When the sub-vectors induced by the blocks have certain limits parametrized by H"usler-Reiss distributions, the global Markov property of the original field induces a particular structure on the parameter matrix of the limiting max-stable H"usler-Reiss distribution. The multivariate Pareto version of the latter turns out to be an extremal graphical model according to the original block graph. Thanks to these algebraic relations, the parameters are still identifiable even if some variables are latent.

Cites work

• A characterization of block graphs
• A Conditional Approach for Multivariate Extreme Values (with Discussion)
• Asymptotic Statistics
• Asymptotics of Markov kernels and the tail chain
• Composite likelihood estimation for the Brown-Resnick process
• Conditional independence among max-stable laws
• Conditional independence in max-linear Bayesian networks
• Estimation of Hüsler–Reiss Distributions and Brown–Resnick Processes
• Extremal behaviour of stationary Markov chains with applications
• EXTREMAL DEPENDENCE: INTERNET TRAFFIC APPLICATIONS
• Extreme events of Markov chains
• Extreme value properties of multivariate t copulas
• Extreme value theory. An introduction.
• Graphical Models for Extremes
• Hidden regular variation and the rank transform
• Hidden regular variation, second order regular variation and asymptotic independence
• scientific article; zbMATH DE number 4030574 (Why is no real title available?)
• scientific article; zbMATH DE number 1085999 (Why is no real title available?)
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• Inference on extremal dependence in the domain of attraction of a structured Hüsler-Reiss distribution motivated by a Markov tree with latent variables
• Limit laws for random vectors with an extreme component
• Limit theory for multivariate sample extremes
• Markov tail chains
• Max-linear models on directed acyclic graphs
• Maxima of normal random vectors: Between independence and complete dependence
• Multivariate generalized Pareto distributions
• Multivariate generalized Pareto distributions: parametrizations, representations, and properties
• On the likelihood function of Gaussian max-stable processes
• One- versus multi-component regular variation and extremes of Markov trees
• Statistics for near independence in multivariate extreme values
• Statistics of Extremes
• Structure Learning for Extremal Tree Models
• The extremal index for a Markov chain
• The extremal index of a higher-order stationary Markov chain
• The square of a block graph
• Variational Analysis

Cited in

(6)

• Max-linear graphical models with heavy-tailed factors on trees of transitive tournaments
• Hidden tail chains and recurrence equations for dependence parameters associated with extremes of stationary higher-order Markov chains
• Graphical models for infinite measures with applications to extremes
• Statistical Inference for Hüsler–Reiss Graphical Models Through Matrix Completions
• Extremal graphical modeling with latent variables via convex optimization
• Learning extremal graphical structures in high dimensions

This page was built for publication: Extremes of Markov random fields on block graphs: max-stable limits and structured Hüsler-Reiss distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6176326)