A matrix exponential spatial specification

Document Type

Article

Publication Date

9-1-2007

Abstract

We introduce the matrix exponential as a way of modelling spatially dependent data. The matrix exponential spatial specification (MESS) simplifies the log-likelihood allowing a closed form solution to the problem of maximum-likelihood estimation, and greatly simplifies the Bayesian estimation of the model. The MESS can produce estimates and inferences similar to those from conventional spatial autoregressive models, but has analytical, computational, and interpretive advantages. We present maximum likelihood and Bayesian approaches to the estimation of this spatial model specification along with methods of model comparisons over different explanatory variables and spatial specifications. © 2006 Elsevier B.V. All rights reserved.

Publication Source (Journal or Book title)

Journal of Econometrics

First Page

190

Last Page

214

This document is currently not available here.

Share

COinS