The MCMC Instrumental Variable Quantile Estimation Of Spatial Autoregressive Models

We study the quantile estimation of spatial autoregressive models under the framework of generalized method of moments,using the Markov Chain Monte Carlo methods to overcome the computational difficulties,which gives the quasi-Beysian estimator,so that we provide a new estimation method for the quantile estimation of spatial autoregressive models.We introduce the spatial autoregressie model under quantile restriction and its estimation method.Based on the large sample theory of nonlinear spatial econometric models and the theory of quasi-Bayesian estimation,we analyze the normal approximation of the quasi-posterior probability density function and the consistency and asymptotic normality of the quasi-Bayesian estimator?Simulation studies are done to investigate the finite sample performance of the quasi-Bayesian estimator.