The aim of this paper is to find a modeling approach for spatially and temporally structured data. The spatial distribution is considered to form an irregular lattice with a specified definition of neighborhood. Additional to the spatial component, a temporal autoregressive parameter, and a time trend are modeled within a multivariates Markov process. This Markov process can be expressed on the basis of an innovation process, which allows for statistical inference on various parameters.
Lattice data conditional autoregressive approach spatio-temporal linear model innovation process ML-estimation