Estimating Spatial Econometrics Models with Integrated Nested Laplace Approximation

The integrated nested Laplace approximation (INLA) provides a fast and effective method for marginal inference in Bayesian hierarchical models. This methodology has been implemented the R-INLA package which permits INLA to be used from within R statistical software. Although is as general methodology, its use practice limited models package. Spatial autoregressive are widely spatial econometrics but have until now lacking In this paper, we describe implementation application of new class latent made available through R-INLA. implements standard lag model. model also means that all other features can fitting, selection econometrics, will shown paper. Finally, illustrate applications with two data sets based on Gaussian binary outcomes.