Dependence matrices for spatial extreme events. Issue 21 (1st November 2016)

• Record Type: Journal Article
• Authors: Fonseca, C.; Martins, A. P.; Pereira, L.; Ferreira, H.
• Is Part Of: Communications in statistics. Volume 45:Issue 21(2016)
• Page Start: 6321
• Page End: 6341
• Publication Date: 2016-11-01
• Subjects: Random field -- Extremal dependence -- Max-stable process; 60G70 -- 62G32; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2013.781649
• Languages: English
• ISSNs: 0361-0926

Abstract

ABSTRACT: If a spatial process is isotropic then the usual pairwise extremal dependence measures depend only on the distance ‖i −j ‖ between the locationsi andj . Nevertheless, in general, we need to evaluate the spatial dependence in different directions of . In this paper, we consider matrices of multivariate tail and extremal coefficients where we table the degrees of dependence for chosen pairs of setsA andB of locations. In this multidirectional approach, the well-known relation between the bivariate tail dependence λ and the extremal ε coefficients, λ = 2 − ϵ, is generalized and new properties arise. The measure matrices here defined to describe spatial dependence are used in several random fields, including a new space time ARMAX storage model and an M4 random field.