Non-parametric estimators of multivariate extreme dependence functions
Authors:
- 1 December 2005
- journal article
- research article
- Published by Taylor & Francis in Journal of Nonparametric Statistics
- Vol. 17 (8) , 915-935
Abstract
This article reviews various characterizations of a multivariate extreme dependence function A(·). The most important estimators derived from these characterizations are also sketched. Then, a unifying approach, which puts all these estimators under the same framework, is presented. This unifying approach enables us to construct new estimators and, most importantly, to propose an automatic selection method for an unknown parameter on which all the existing non-parametric estimators of A(·) depend. Constrained smoothing splines and convex hull techniques are used to force the obtained estimators to be extreme dependence functions. A simulation study comparing these estimators on a wide range of extreme dependence functions is provided.Keywords
This publication has 30 references indexed in Scilit:
- Exploiting occurrence times in likelihood inference for componentwise maximaBiometrika, 2005
- Nonparametric estimation of the spectral measure of an extreme value distributionThe Annals of Statistics, 2001
- Distribution and Dependence-Function Estimation for Bivariate Extreme-Value DistributionsBernoulli, 2000
- From value at risk to stress testing: The extreme value approachJournal of Banking & Finance, 2000
- Smoothing Splines and Shape RestrictionsScandinavian Journal of Statistics, 1999
- L2Version Of The Double Kernel MethodStatistics, 1999
- Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classesThe Annals of Statistics, 1997
- A nonparametric estimation procedure for bivariate extreme value copulasBiometrika, 1997
- A universally acceptable smoothing factor for kernel density estimatesThe Annals of Statistics, 1996
- Bivariate extreme value theory: Models and estimationBiometrika, 1988