Working Paper BETA #2001-05

Download working-paper

Title : Efficient Estimation of Spatial Autoregressive Models

Author(s) : Théophile AZOMAHOU, Yves KUHRY

Abstract : This paper considers estimating general spatial autoregressive models using the generalized method of moments (GMM). I propose nonparametric estimates of the optimal instruments based on conditional second moment restrictions. We show that these instruments are optimal over all possible instruments, especially over those usually suggested in a spatial context. We provide a consistent nonparametric estimator of sample autocovariances function for irregularly spaced spatial stochastic processes. We then derive a consistent estimator for the asymptotic covariance matrix. Finally we investigate the asymptotic distribution of the GMM estimator.

Key-words : Instrumental variables; Spatialdependence; Nonparametric estimation

JEL Classification : C13; C14; C50