Efficient estimation of the canonical dependence function

DOI10.1023/A:1026229314063MaRDI QIDQ1887259zbMATH OpenFDO

Authors Michael Falk, Rolf-Dieter Reiss

Publication date 24 November 2004

Published in Extremes (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1023/A:1026229314063

zbMATH Keywords

bivariate extreme value distributionlocal asymptotic normality (LAN)Pickands representation

Mathematics Subject Classification ID

Statistics of extreme values; tail inference (62G32) Measures of association (correlation, canonical correlation, etc.) (62H20)

Review text

Any bivariate max-stable (extreme value) distribution \(G\) with reversed standard exponential margins can be represented in the form \[ G(x,y)=\exp ( (x+y) D(y/(x+y))),\quad x,y<0, \] where \(D:[0,1]\to[0,1]\) is the Pickands dependence function. The function \(\vartheta(t)=(1-D(z))/\min(z,1-z)\) is called the canonical dependence function. The problem is to estimate \(D\) and \(\vartheta\) by i.i.d. observations from \(G\). Local asymptotic normality of the loglikelihood function of \(r\times r\) table sorting is demonstrated. Asymptotically normal and efficient estimators are constructed.

Recommendations

• Distribution and dependence-function estimation for bivariate extreme-value distributions.
• Estimation of a bivariate extreme value distribution
• Nonparametric estimation of the dependence function for a multivariate extreme value distribution
• Nonparametric estimation of the dependence function in bivariate extreme value distributions
• Intrinsic estimation of the dependence structure for bivariate extremes

Cited in

(11)

• On the distribution of Pickands coordinates in bivariate EV and GP models
• Efficient estimators and LAN in canonical bivariate POT models.
• Canonical dependency analysis based on squared-loss mutual information
• Canonical spectral representation for exchangeable max-stable sequences
• On the generation of a multivariate extreme value distribution with prescribed tail dependence parameter matrix
• Estimating the tail-dependence coefficient: properties and pitfalls
• Likelihood estimators for multivariate extremes
• Modification of Pickands' dependence function for ordered bivariate extreme distribution
• Non-parametric Estimation of Tail Dependence
• Estimation of canonical dependence parameters in a class of bivariate peaks-over-threshold models
• Multivariate generalized Pareto distributions

This page was built for publication: Efficient estimation of the canonical dependence function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1887259)