CRPS M-estimation for max-stable models

DOI10.1007/S10687-014-0185-XzbMATH Open1309.62100arXiv1307.7209OpenAlexW2593417708MaRDI QIDQ488104FDOQ488104

Stilian Stoev, Robert Yuen

Publication date: 23 January 2015

Published in: Extremes (Search for Journal in Brave)

Abstract: Max-stable random fields provide canonical models for the dependence of multivariate extremes. Inference with such models has been challenging due to the lack of tractable likelihoods. In contrast, the finite dimensional cumulative distribution functions (CDFs) are often readily available and natural to work with. Motivated by this fact, in this work we develop an M-estimation framework for max-stable models based on the continuous ranked probability score (CRPS) of multivariate CDFs. We start by establishing conditions for the consistency and asymptotic normality of the CRPS-based estimators in a general context. We then implement them in the max-stable setting and provide readily computable expressions for their asymptotic covariance matrices. The resulting point and asymptotic confidence interval estimates are illustrated over popular simulated models. They enjoy accurate coverages and offer an alternative to composite likelihood based methods.

Full work available at URL: https://arxiv.org/abs/1307.7209

Recommendations

• Composite likelihood for extreme values
• Likelihood-based inference for max-stable processes
• Statistical Inference for Max-Stable Processes in Space and Time
• MAX-stable models for multivariate extremes
• Multivariate max-stable spatial processes

zbMATH Keywords

M-estimationmultivariate extremesmax-stableCRPS

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12)

Cites Work

• A hierarchical max-stable spatial model for extreme precipitation
• Asymptotic Statistics
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Likelihood-Based Inference for Max-Stable Processes
• Stationary max-stable fields associated to negative definite functions
• A spectral representation for max-stable processes
• Models for stationary max-stable random fields
• Models for dependent extremes using stable mixtures
• Title not available (Why is that?)
• Title not available (Why is that?)
• Spatial modeling of extreme snow depth
• A new test for multivariate normality
• Simulation of Brown-Resnick processes
• Estimation of Hüsler–Reiss Distributions and Brown–Resnick Processes
• Statistical modeling of spatial extremes
• An M-estimator for tail dependence in arbitrary dimensions
• Extreme values of independent stochastic processes
• The Minimum Distance Method
• Approximate Bayesian computing for spatial extremes
• Minimum Distance and Robust Estimation
• Dense classes of multivariate extreme value distributions
• Title not available (Why is that?)
• Spectral representations of sum- and max-stable processes
• Extremal stochastic integrals: a parallel between max-stable processes and \(\alpha\)-stable processes
• On the ergodicity and mixing of max-stable processes

Cited In (4)

• Simultaneous autoregressive models for spatial extremes
• \(k\)-means clustering of extremes
• Spatial risk measures and applications to max-stable processes
• Upper bounds on value-at-risk for the maximum portfolio loss

Uses Software

• SpatialExtremes
• evd

This page was built for publication: CRPS M-estimation for max-stable models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q488104)