Use este identificador para citar ou linkar para este item:
https://www.arca.fiocruz.br/handle/icict/35539
Tipo de documento
ArtigoDireito Autoral
Acesso restrito
Objetivos de Desenvolvimento Sustentável
07 Energia limpa e acessívelColeções
Metadata
Mostrar registro completo
BAYESIAN SPATIO-TEMPORAL MODELS BASED ON DISCRETE CONVOLUTIONS
Spatial models
Covariance matrices
Time series
Spacetime
Statistical variance
Multilevel models
Interpolation
Scale modeling
Spectral energy distribution
Afiliação
University of California at Santa Cruz. Department of Applied Mathematics and Statistics. Santa Cruz, CA, USA.
Universidade Federal do Rio de Janeiro. Instituto de Matemática. Rio de Janeiro, RJ, Brasil.
Oswaldo Cruz Foundation. Presidency. Scientific Computing Program. Rio de Janeiro, RJ, Brazil.
Universidade Federal do Rio de Janeiro. Instituto de Matemática. Rio de Janeiro, RJ, Brasil.
Oswaldo Cruz Foundation. Presidency. Scientific Computing Program. Rio de Janeiro, RJ, Brazil.
Resumo em Inglês
The authors consider a class of models for spatio-temporal processes based on convolving independent processes with a discrete kernel that is represented by a lower triangular matrix. They study two families of models. In the first one, spatial Gaussian processes with isotropic correlations are convoluted with a kernel that provides temporal dependencies. In the second family, AR(p) processes are convoluted with a kernel providing spatial interactions. The covariance structures associated with these two families are quite rich. Their covariance functions that are stationary and separable in space and time as well as time dependent nonseparable and nonisotropic ones. /// Les auteurs s'intéressent à une classe de modèles pour les processus spatio-temporels basés sur la convolution de processus indépendants avec un noyau discret représenté par une matrice triangulaire inférieure. Ils étudient deux familles de modèles. Dans la première, des processus spatiaux gaussiens à corrélations isotropes sont convolués avec un noyau induisant des dépendances temporelles. Dans la seconde, des processus AR(p) sont convolués avec un noyau induisant des interactions spatiales. Les structures de covariance associées à ces deux familles sont très riches. Leurs fonctions de covariance peuvent être stationnaires et séparables dans l'espace et dans le temps ou encore dépendantes du temps, non séparables et non isotropes.
Palavras-chave em inglês
CovarianceSpatial models
Covariance matrices
Time series
Spacetime
Statistical variance
Multilevel models
Interpolation
Scale modeling
Spectral energy distribution
Compartilhar