Dear list, Is there a way to fit in R a multilevel model that accounts for the spatial proximity/neighborhood that may exist between the cases in the first level?
I have found some older questions in R lists related to this issue, but all related to fitting more complex models and usually with spatial correlation in the higher-levels, what is a diferente task. My first-level units are counties and second-level units are states. In my model I have theoretical reasons to expect the countries of a same state to be spatially correlated. While there is no reason to expect counties to be spatially related to the counties of other states. Thanks, Ferdinand V. Bersse [[alternative HTML version deleted]] _______________________________________________ R-sig-Geo mailing list R-sig-Geo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-geo