Historically, it has been difficult to apply spatial statistics to large datasets (e.g., more than 10,000 observations). This site contains public domain spatial software written in Matlab (Matlab Spatial Statistics Toolbox 2.0) capable of estimating very large spatial autoregressions (e.g., one example involves 1,000,000 observations). The spatial software uses sparse matrix methods to compute the matrix determinants employed in the maximum likelihood estimation of the spatial autoregressions. Specifically, the software can estimate simultaneous spatial autoregressions (SAR), conditional spatial autoregressions (CAR), mixed regressive spatially autoregressive (MRSA) estimates as well as other lattice models which are the mainstay of spatial econometrics. Version 1.1 contained routines for specifying dependence via nearest neighbors or contiguity, exact log-determinant computations, and closed form maximum likelihood estimation of closest neighbor dependence.

Check http://www.spatial-statistics.com/ for downloading.