Regression Analysis in a Data Rich Environment

This paper discusses a number of conceptual issues pertaining to the study of the relationships existing between two groups of dependent and regressor variables which are supposed to be spatially and temporally correlated. Since it is assumed that this relationships can be studied in a reduced latent space, we propose a factor analytic approach and provide an overview of the motivations for including spatial effects in dynamic factor models. Considerable attention is paid to the inferential framework necessary to carry out estimation and to the different assumptions, constraints and implications embedded in the various model specifications. The discussion combines insights from the traditional (spatial) econometrics literature as well as from geostatistics and image analysis.