Testing the assumption of independence between variables is a crucial aspect of spatial data analysis. However, the literature is limited and somewhat confusing. To our knowledge, we can mention only the bivariate generalization of Moran’s statistic. This test suffers from several...

Testing for the assumption of independence between spatial variables is an important first step in spatial conometrics. Usually the researchers use the bivariate generalization of the Moran’s statistic, specifying a spatial matrix a priori. This test is applicable only to detect linear...

The purpose of this paper is to show the capacity of a new non-parametric test based on symbolic entropy and symbolic dynamics to deal with the detection of linear and non-linear spatial causality. The good performance of the new test in detecting spatial causality and causal weighting matrix is...

The paper shows a new non-parametric test, based on symbolic entropy, which permits detect spatial causality in cross-section data. The test is robust to the functional form of the relation and has a good behaviour in samples of medium to large size. We illustrate the use of test with the case...

In spatial econometrics, it is customary to specify a weighting matrix, the so-called W matrix. The decision is important because the choice of W matrix determines the rest of the analysis. However, the procedure is not well defined and, usually, reflects the priors of the user. In the paper, we...