基于高维标度评价法的数字经济发展水平评价  

Evaluation of Digital Economy Development Level Based on MDS Evaluation Method

作　　者：魏艳华[1] 王丙参[1] 马立平[2] Wei Yanhua;Wang Bingcan;Ma Liping(School of Mathematics and Statistics,Tianshui Normal University,Tianshui Gansu 741001,China;School of Statistics,Capital University of Economics and Business,Beijing 100070,China)

机构地区：[1]天水师范学院数学与统计学院,甘肃天水741001 [2]首都经济贸易大学统计学院,北京100070

出　　处：《统计与决策》2024年第20期73-77,共5页Statistics & Decision

基　　金：国家社会科学基金资助项目(20BTJ027);天水师范学院高层次人才科研项目(KYQ2023-25)。

摘　　要：文章构建多种形式的高维标度评价法(MDSEM),该系列方法从评价对象间距离矩阵出发,更适用于小样本。当采用欧氏距离时,MDSEM等价于第一主成分评价法,基于熵权Minkowski距离的MDSEM可提高评价结果的一致性。基于MDSEM对2013—2020年中国数字经济发展水平进行测度并分析其时空分布特征,结果表明:中国数字经济发展水平呈现空间集聚特征,上海、江苏、浙江、北京、天津等东部地区省份相互促进、高水平运转,而大多数中西部地区省份则处于低-低弱集聚状态;区域差异较大,总体Gini系数先下降后略有上升,区间Gini系数贡献率在高位震荡下降,主要取决于东-中部、东-西部差异;从省份排名来看,2013—2020年,贵州、湖南、河北、江西等进步较大,而宁夏、新疆、黑龙江、山西等退步较大;5种数字经济发展状态较为稳定,跃级转移几乎不可能发生,稳态分布呈现橄榄球形状,较为合理。This paper constructs various forms of Multidimensional scaling evaluation method(MDSEM).This series of meth⁃ods start from the distance matrix between objects and are more suitable for small samples.When Euclidean distance is used,MD⁃SEM is equivalent to the first principal component evaluation method,and MDSEM based on entropy weight Minkowski distance can improve the consistency of evaluation results.The paper is based on MDSEM to measure the development level of China's digital economy from 2013 to 2020 and analyze its temporal and spatial distribution characteristics.The research results are shown as follows:The development level of China's digital economy presents the characteristics of spatial agglomeration.The east⁃ern provinces such as Shanghai,Jiangsu,Zhejiang,Beijing and Tianjin promote each other and operate at a high level,while most provinces in the central and western regions are in a low-low and weak agglomeration state.The overall Gini coefficient decreases at first and then increases slightly,and the contribution rate of the interval Gini coefficient decreases at a high level,which main⁃ly depends on the east-central difference and east-west difference.In terms of provincial rankings,from 2013 to 2020,Guizhou,Hunan,Hebei,Jiangxi,etc.,made great progress,while Ningxia,Xinjiang,Heilongjiang,Shanxi,etc.,showed great regression.The development state of the five digital economies is relatively stable;the step transfer is almost impossible to occur,and the steady state distribution presents the shape of a football,which is more reasonable.

关 键 词：高维标度评价法 数字经济 地区差异 莫兰指数 

分 类 号：O29[理学—应用数学] F49[理学—数学]