New estimators of the Pickands dependence function and a test for extreme-value dependence

DOI10.1214/11-AOS890zbMATH Open1306.62087arXiv1102.0405OpenAlexW3099482564MaRDI QIDQ651018FDOQ651018

Authors: Axel Bücher, Stanislav Volgushev, Holger Dette 

Publication date: 8 December 2011

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We propose a new class of estimators for Pickands dependence function which is based on the concept of minimum distance estimation. An explicit integral representation of the function $A^{\ast }(t)$, which minimizes a weighted $L^2$-distance between the logarithm of the copula $C(y^{1-t},y^t)$ and functions of the form $A(t)log(y)$ is derived. If the unknown copula is an extreme-value copula, the function $A^{\ast }(t)$ coincides with Pickands dependence function. Moreover, even if this is not the case, the function $A^{\ast }(t)$ always satisfies the boundary conditions of a Pickands dependence function. The estimators are obtained by replacing the unknown copula by its empirical counterpart and weak convergence of the corresponding process is shown. A comparison with the commonly used estimators is performed from a theoretical point of view and by means of a simulation study. Our asymptotic and numerical results indicate that some of the new estimators outperform the estimators, which were recently proposed by Genest and Segers [Ann. Statist. 37 (2009) 2990--3022]. As a by-product of our results, we obtain a simple test for the hypothesis of an extreme-value copula, which is consistent against all positive quadrant dependent alternatives satisfying weak differentiability assumptions of first order.

Full work available at URL: https://arxiv.org/abs/1102.0405

Recommendations

• Minimum distance estimators of the Pickands dependence function and related tests of multivariate extreme-value dependence
• Projection estimators of Pickands dependence functions
• Nonparametric estimation of multivariate extreme-value copulas
• Rank-based inference for bivariate extreme-value copulas
• A goodness-of-fit test for bivariate extreme-value copulas

zbMATH Keywords

extreme-value copulaPickands dependence functionweak convergenceempirical copula processminimum distance estimationtest for extreme-value dependence

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Statistics of extreme values; tail inference (62G32)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Introduction to empirical processes and semiparametric inference
• On the limiting behavior of the Pickands estimator for bivariate extreme- value distributions
• Distribution and dependence-function estimation for bivariate extreme-value distributions.
• Weak convergence of empirical copula processes
• Maxima of normal random vectors: Between independence and complete dependence
• Nonparametric estimation of the dependence function for a multivariate extreme value distribution
• Title not available (Why is that?)
• Title not available (Why is that?)
• A nonparametric estimation procedure for bivariate extreme value copulas
• Title not available (Why is that?)
• Projection estimators of Pickands dependence functions
• Title not available (Why is that?)
• New estimators of the Pickands dependence function and a test for extreme-value dependence
• An introduction to copulas.
• Rank-based inference for bivariate extreme-value copulas
• Title not available (Why is that?)
• Semiparametric estimation in copula models
• A kolmogorov-smirnov type test for positive quadrant dependence
• Families of min-stable multivariate exponential and multivariate extreme value distributions
• Title not available (Why is that?)
• A note on bootstrap approximations for the empirical copula process
• Dependence measures for extreme value analyses
• Asymptotic distributions of multivariate rank order statistics
• Title not available (Why is that?)
• Bivariate extreme value theory: Models and estimation
• Nonparametric rank-based tests of bivariate extreme-value dependence
• Extreme value theory for multivariate stationary sequences
• Propriétés statistiques des copules de valeurs extrêmes bidimensionnelles
• On the Ghoudi, Khoudraji, and Rivest test for extreme-value dependence
• Nonparametric estimation of the dependence function in bivariate extreme value distributions
• Asymptotically minimax estimators for distributions with increasing failure rate

Cited In (45)

• Extreme value analysis of multivariate high-frequency wind speed data
• Minimum distance estimators of the Pickands dependence function and related tests of multivariate extreme-value dependence
• A comparison of dependence function estimators in multivariate extremes
• Robust quantile estimation under bivariate extreme value models
• A moment-based test for extreme-value dependence
• Regular variation, conditions of domain of attraction and the existence of the tail dependence function in the general dependence case: a copula approach
• TESTING FOR HOMOGENEITY IN MIXTURE MODELS
• Some copula inference procedures adapted to the presence of ties
• Nonparametric Identification of Copula Structures
• Weighted least-squares inference for multivariate copulas based on dependence coefficients
• A test for truncation invariant dependence
• Local robust estimation of the Pickands dependence function
• Bias correction in multivariate extremes
• Weak convergence of the weighted empirical beta copula process
• Exceedance-based nonlinear regression of tail dependence
• Testing asymmetry in dependence with copula-coskewness
• Parametric and non-parametric estimation of extreme earthquake event: the joint tail inference for mainshocks and aftershocks
• Estimating multivariate extremal dependence: a new proposal
• Expansions of multivariate Pickands densities and testing the tail dependence
• Nonparametric inference for max-stable dependence
• Multivariate nonparametric estimation of the Pickands dependence function using Bernstein polynomials
• Copula modeling from Abe Sklar to the present day
• Tail-weighted dependence measures with limit being the tail dependence coefficient
• Using B-splines for nonparametric inference on bivariate extreme-value copulas
• Estimation of Pickands dependence function of bivariate extremes under mixing conditions
• A general approach to the joint asymptotic analysis of statistics from sub-samples
• Graphical and formal statistical tools for the symmetry of bivariate copulas
• Nonparametric estimation of multivariate extreme-value copulas
• Projection estimators of Pickands dependence functions
• Reweighted madogram-type estimator of Pickands dependence function
• Polynomial Pickands functions
• Nonparametric estimation of an extreme-value copula in arbitrary dimensions
• New estimators of the Pickands dependence function and a test for extreme-value dependence
• Asymptotic behavior of an intrinsic rank-based estimator of the Pickands dependence function constructed from B-splines
• GOODNESS-OF-FIT TESTS FOR MULTIVARIATE COPULA-BASED TIME SERIES MODELS
• Bias-corrected and robust estimation of the bivariate stable tail dependence function
• Bivariate nonparametric estimation of the Pickands dependence function using Bernstein copula with kernel regression approach
• Rank-based inference for bivariate extreme-value copulas
• Bayesian estimation of bivariate Pickands dependence function
• Mass distributions of two-dimensional extreme-value copulas and related results
• Extreme value copula estimation based on block maxima of a multivariate stationary time series
• On the limiting behavior of the Pickands estimator for bivariate extreme- value distributions
• Jackknife empirical likelihood test for the equality of degrees of freedom in t-copulas
• Robust bounds in multivariate extremes
• Weighted estimation of the dependence function for an extreme-value distribution

Uses Software

• fdrtool
• Kernlab

This page was built for publication: New estimators of the Pickands dependence function and a test for extreme-value dependence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q651018)