A flexible dependence model for spatial extremes
Autor: | Carlo Gaetan, Jean-Noël Bacro, Gwaldys Toulemonde |
---|---|
Přispěvatelé: | Institut Montpelliérain Alexander Grothendieck (IMAG), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Dipartimento di Scienze Ambientali, Informatica e Statistica [Venezia] (DAIS), University of Ca’ Foscari [Venice, Italy] |
Rok vydání: | 2016 |
Předmět: |
Spatial extremes
Asymptotic independence Max-stable processes MAX-STABLE PROCESSES INFERENCE LIKELIHOOD GEOSTATISTICS MULTIVARIATE STATISTICS VALUES SPACE TIME Statistics and Probability Multivariate statistics 010504 meteorology & atmospheric sciences Structure (category theory) Spatial extremes 01 natural sciences LIKELIHOOD 010104 statistics & probability Asymptotic independence [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] Econometrics SPACE Statistical physics 0101 mathematics Spatial dependence Extreme value theory ComputingMilieux_MISCELLANEOUS Independence (probability theory) 0105 earth and related environmental sciences Mathematics VALUES Applied Mathematics Max-stable processes MAX-STABLE PROCESSES Extension (predicate logic) STATISTICS TIME MULTIVARIATE INFERENCE Pairwise comparison GEOSTATISTICS Statistics Probability and Uncertainty Settore SECS-S/01 - Statistica Maxima |
Zdroj: | Journal of Statistical Planning and Inference Journal of Statistical Planning and Inference, Elsevier, 2016, 172, pp.36-52. ⟨10.1016/j.jspi.2015.12.002⟩ |
ISSN: | 0378-3758 1873-1171 |
Popis: | Max-stable processes play a fundamental role in modeling the spatial dependence of extremes because they appear as a natural extension of multivariate extreme value distributions. In practice, a well-known restrictive assumption when using max-stable processes comes from the fact that the observed extremal dependence is assumed to be related to a particular max-stable dependence structure. As a consequence, the latter is imposed to all events which are more extreme than those that have been observed. Such an assumption is inappropriate in the case of asymptotic independence. Following recent advances in the literature, we exploit a max-mixture model to suggest a general spatial model which ensures extremal dependence at small distances, possible independence at large distances and asymptotic independence at intermediate distances. Parametric inference is carried out using a pairwise composite likelihood approach. Finally we apply our modeling framework to analyze daily precipitations over the East of Australia, using block maxima over the observation period and exceedances over a large threshold. |
Databáze: | OpenAIRE |
Externí odkaz: |