1
عمومی::
مدل خطای فضایی
These two models - Kelejian-Prucha and SDM - include specific sub-models, i.e. the autore- gressive spatial model (SAR, AutoRegression spatial): Y = r ·WY +X · b +e) and the model with spatially auto-correlated errors (SEM, Spatial Error Model): Y = X · b +u and u = l ·Wu +e).
By noting u = Y X · b, it results in the SEM model.
The Lagrange multiplier tests (Anselin et al. 1996 for the SAR and SEM model specification tests, robust to the presence of other types of spatial interactions), then make it possible to choose between the SAR, SEM or non-spatial model.
Florax et al. 2003 have also shown, using simulations, that this procedure was the most effective when the real model is a SAR or SEM model.
It consists in starting with the bottom-up approach but, in the event of spatial interaction (r = 0 or l = 0), instead of directly choosing a SAR or SEM model, studying the Durbin spatial model.
واژگان شبکه مترجمین ایران