一类变系数空间滞后的混合地理加权回归模型OA北大核心CSTPCD

Spatial correlation and spatial heterogeneity are the theoretical basis of spatial econometrics.In order to solve the local problem of spatial lag of dependent variables,this study extended the existing mixed geographically weighted regression model with constant-coefficient spatial lag,and proposed a mixed geographically weighted regression model with varying-coefficient spatial lag.The mixed geographically weighted regression model with varying-coefficient spatial lag combines spatial correlation with spatial heterogeneity,and covers most of the model forms of geographically weighted regression.Based on the parameterization reconstruction method and likelihood ratio test,the coefficient estimation method,significance test of this model and the discriminant test of varying-coefficient are given respectively.Both in Monte Carlo simulation and practical application,the results show that the mixed geographically weighted regression model with varying-coefficient spatial lag renders itself well for the fitting and forecasting effect on dependent variable.The mixed geographically weighted regression model with varying-coefficient spatial lag provides a support for setting up a suitable model form for quantitative research on spatial effects.