koschins at uiuc.edu
Thu Nov 29 14:58:08 CST 2007
There's a body of literature with theoretical proofs for consistent/optimal spatial 2SLS estimators with WX (and transformed versions of WX) instruments for Wy, e.g.:
Kelejian and Prucha. (1998). A Generalized Spatial Two-Stage Least Squares Procedure for Estimating a Spatial Autoregressive Model with Autoregressive Disturbances. Journal of Real Estate Finance and Economics, Vol. 17:1, 99-121.
Lung-fei Lee. (2003). Best Spatial Two-Stage Least Squares Estimators for a Spatial Autoregressive Model with Autoregressive Disturbances. ECONOMETRIC REVIEWS, Vol. 22, No. 4, pp. 307–335.
R's spdep package includes a spatial 2SLS estimator with WX instruments for Wy.
More information about the Openspace