CIRJE-F-587. Yajima, Yoshihiro and Yasumasa Matsuda, "Asymptotic Properties of the LSE of a Spatial Regression in both Weakly and Strongly Dependent Stationary Random Fields", September 2008.

We consider asymptotic properties of the least squares estimator(LSE) in spatial regression with correlated errors. Firstly we derive sufficient conditions for the LSE to be strongly consistent and next necessary and/or sufficient conditions tor the LSE to be asymptotically efficient relative to the best liner unbiased estimator(BLUE). Finally we derive the asymptotic distribution of the LSE under conditions on the higher order cumulants of the error terms and the Fourier transforms of the regressors. The main feature is that we propose a unified way in which we can deal with both weakly dependent and strongly dependent error terms.