Spatial Trends and Spatial Econometric Structures: practical application to a different context data

Abstract

Spatial trend concept was proved to be useful to depict the systematic variations of the phenomenon concerned over a region based on geographical locations. We use three different geographical datasets to check if there exist potential leading deterministic spatial components and whether we can econometrically model spatial economic relations that might contain unobserved spatial structure of unknown form. Hypothesis testing is conducted with a symbolic-entropy based non-parametric statistical procedure, proposed in Garcia-Cordoba et al. (2019), which does not rely on prior weight matrices assumptions. Geographically restricted semiparametric spatial models are taken to perform a modeling strategy for crosssectional data sets. The main question to be responded is whether the models that merely incorporate space coordinates might be sufficient to capture space dependence when applied to different types of data. Moreover, it is important to study what intrinsic characteristics of the economic problem or the dependent variable itself make feasible (and optimal) to use the specific methodological approach.