3.3.4. Spatial Regression Model

Due to the significant spatial correlation of environmental innovation with cities in China, a spatial panel regression model was considered for the detection of the determinants. By comparing the spatial lag model (SLM), the spatial error model (SEM), and the spatial Durbin model (SDM) based on Stata 12.0 analysis, it was found that the goodness of fit and credibility of the SDM (R² = 0.863) was the highest among the three models, and the Hausman test results showed that the SDM random effects passed the robustness test. Therefore, this paper selected the SDM with random effects to analyze the determinants of environmental innovation of cities in China:

where i indexes the city, and t indexes time.