Find in Library

The practice of spatial econometrics revolves around a weighting matrix, which is often supplied by the user on previous knowledge. This is the so-called <inline-formula> <math display="inline"> <semantics> <mi mathvariant="bold">W</mi> </semantics> </math> </inline-formula> issue. Probably, the aprioristic approach is not the best solution although, presently, there are few alternatives for the user. Our contribution focuses on the problem of selecting a <inline-formula> <math display="inline"> <semantics> <mi mathvariant="bold">W</mi> </semantics> </math> </inline-formula> matrix from among a finite set of matrices, all of them considered appropriate for the case. We develop a new and simple method based on the entropy corresponding to the distribution of probability estimated for the data. Other alternatives, which are common in current applied work, are also reviewed. The paper includes a large study of Monte Carlo to calibrate the effectiveness of our approach compared to others. A well-known case study is also included.