混合地理加权空间自回归模型的Profile GMM估计

Profile GMM Estimation in Mixed Geographically Weighted Spatial Autoregressive Models

为了更好地同时考虑空间自相关性和空间异质性,本文研究一类空间自回归混合地理加权回归模型.基于Profile方法和广义矩(GMM)方法,构造了模型中未知空间自回归参数,常数回归系数和系数函数的两类Profile GMM估计.数值模拟结果表明所提出的估计在有限样本中表现良好.

To deal simultaneously with spatial autocorrelation and spatial heterogeneity,this paper considers a mixed geographically weighted spatial autoregressive model.Based on the profile method and Generalized Method of Moments approach,two kinds of profile GMM estimators of the unknown spatial autoregressive parameter and constant regression coefficients,as well as nonparametric functions are proposed.Some simulations are conducted to examine the performance of our proposed methods and the results are satisfactory.