HAL : hal-00361245, version 2

arXiv : 0902.3060

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

Versions disponibles :

v1 (18-02-2009)

v2 (23-02-2009)

Likelihood-based inference for max-stable processes

Simone A. Padoan 1, Mathieu Ribatet 2, Scott A. Sisson 3

(17/10/2008)

The last decade has seen max-stable processes emerge as a common tool for the statistical modeling of spatial extremes. However, their application is complicated due to the unavailability of the multivariate density function, and so likelihood-based methods remain far from providing a complete and flexible framework for inference. In this article we develop inferentially practical, likelihood-based methods for fitting max-stable processes derived from a composite-likelihood approach. The procedure is sufficiently reliable and versatile to permit the simultaneous modeling of marginal and dependence parameters in the spatial context at a moderate computational cost. The utility of this methodology is examined via simulation, and illustrated by the analysis of U.S. precipitation extremes.

1 :	Laboratory of Environmental Fluid Mechanics and Hydrology (EFLUM)
	École Polytechnique Fédérale de Lausanne
2 :	Chair of Statistics
	École Polytechnique Fédérale de Lausanne
3 :	School of Mathematics and Statistics
	University of New South Wales

Domaine

:

Statistiques/Méthodologie

hal-00361245, version 2

http://hal.archives-ouvertes.fr/hal-00361245/fr/

oai:hal.archives-ouvertes.fr:hal-00361245_v2

Contributeur : Mathieu Ribatet <>

Soumis le : Samedi 21 Février 2009, 16:00:28

Dernière modification le : Lundi 23 Février 2009, 08:02:18