多维贫困的空间聚类与相关性研究

Study on Spatial Clustering and Correlation of Multidimensional Poverty

区域多维贫困是2020年后我国减贫事业的重要导向,也是减贫理论研究的重要内容。基于2010、2012、2014、2016、2018年全国31个省市自治区的相关数据,运用主成分分析、系统聚类分析和Moran’sI指数分析的方法研究了各省际区域多维贫困的空间聚类情况及其相关性,以此来分析我国各地区多维贫困的空间特征和区域差别。结果表明:我国各个地区的多维贫困存在程度上的差异,其中北京等地区已逐步脱离多维贫困,西藏等地区存在严重的多维贫困问题,其余地区则呈现不同程度上的多维贫困。同时,各地区的多维贫困存在地理上的空间自相关。在此基础上,提出空间性的多维贫困治理的建议。

Regional multidimensional poverty is an important direction of China’s poverty reduction after 2020,and also an important content of theoretical research on poverty reduction.Based on the 2010,2012,2014,2016 and 2018,the related data of 31 provinces,cities and autonomous regions nationwide,using principal component analysis,system cluster analysis and Moran’s I index analysis method to study the various provincial regional spatial clustering of multidimensional poverty and its correlation,in order to analyze our country regional spatial characteristic and regional difference of multidimensional poverty.The results show that there are differences in the degree of multi-dimensional poverty in various regions of China,among which Beijing and other regions have gradually got rid of multi-dimensional poverty,Tibet and other regions have serious multi-dimensional poverty,and other regions have shown multi-dimensional poverty in different degrees.At the same time,there is a spatial autocorrelation between the multidimensional poverty in different regions.On this basis,the paper puts forward some Suggestions on spatial and multidimensional poverty management.