Modelagem espaço-temporal para campos aleatórios gaussianos transformados

Abstract

Models that are capable of capturing the spatial and temporal characteristics of the data are applicable in many science fields. Non-separable spatio-temporal models were introduced in the literature to capture these features, however, these models are usuallycomplicated in its interpretation and construction. In this work, we introduce a class of non-separable Transformed Gaussian Markov Random Fields (TGMRF) where the dependence structure is not only flexible but also provides simple interpretation to the spatial, temporal and spatio-temporal parameter in the random effects. Another advantageis that the TGMRF settings allow specialists to define any desired margins. Therefore, the construction of spatio-temporal models using the TGMRF framework leads to a new class of models such as spatio-temporal gamma random fields, that can be direclty usedto model Poisson intensity for space-time data. The proposed models were applied to the abundance data of Nenia Tridens to pick out important environmental variables that affect their abundance and also study possible spatial and temporal trends.