Spatial Statistics Analysis Of Economy And Environment In Jiangsu Province

Different regions have different models, because of spatial dimension, traditional statistics analysis, based on time dimension, is not precise, under the strict assumptions such as the sample of independent and identically distributed in a homogeneous space. Spatial statistics, as a new multidimensional data analysis method, solve a series of problems such as spatial autocorrelation and spatial heterogeneity effectively. This paper describes two spatial data analysis methods: spatial econometric model and geostatistics model. This paper uses two examples to analysis spatial data from two aspects of economy and environment. Spatial econometric model analyzes Jiangsu economic spatial correlation, meanwhile, geostatistics model is used to explore the spatial variation of PM2.5and its influencing factors.This paper selected region economic data in Jiangsu Province. This paper analyzed the spatial characteristics of economic development by Moran’s1, and used the spatial econometrics models to explore influencing factors of economic development. The results show that cities have strong spatial aggregation, which means spatial autocorrelation; economic development has tight space contact, population capital and urbanization play important roles on economic growth. After introducing the spatial weight matrix, the spatial econometrics model is better than the traditional linear regression significantly.PM2.5is one of the important factors that cause air pollution. In order to analyze spatial variation of PM2.5, geostatistics was used to analyze PM2.5pollution based on Jiangsu PM2.5monitoring station data. The results show that Exponential model is better than Spherical model and Gaussian model; sunny, rainy, snowy is moderate variability, spatial variation is caused by structural and stochastic factors; the nugget coefficient in sunny is16.7%, Spatial correlation is strong, but the nugget coefficients in rainy and snowy are relatively weak, they confirm that rain and snow have a larger impact on PM2.5.