基于主成分分析法的人类发展指数替代技术

An Alternative to Human Development Index with Principal Component Analysis

在本文中,我们采用基于协方差的主成分分析法来分析1990年以来UNDP发布的中国人类发展数据,然后采用Spearman秩相关系数来分析获得的主成分与HDI之间的关系。研究表明,主成分分析法不仅能够有效地替代传统的人类发展指数编制方法,其形成的动态权重结构还可以有效地透视人类发展差距模式的历史演进过程,以及人类发展的各个方面(如预期寿命、知识教育和体面的生活等)在整体发展进程中的角色变化。对中国人类发展数据的分析结果也表明,尽管1990年以来中国各地区在经济、教育和健康方面均取得了重大进步,但三项发展之间存在着严重的不协调,地区发展差距也越来越多地体现为经济发展差距,这些反映了改革开放以来中国各级政府过分强调经济增长而带来的片面、不协调的人类发展。实现经济社会的协调发展,是时代的要求,也是当前我国各级政府面临的主要任务。而强调公共服务职能、推动地方政府的服务型转型,是消除不平衡发展的关键。

In this study, we used the Covariance-based Principal Component Analysis (PCA) to measure and analyze the progress of human development in Chinese provinces since 1990. The association of the main principal component obtained from our study and the China human development index reported by the United Nations Development Programme was estimated by the Spearman's rank correlation coefficient. This study suggested that PCA can be used as an effective alternative to traditional HDI technique. In addition, by examining the dynamic weight structure derived from PCA, we can track the changing roles of different aspects, like longevity, knowledge and decent standard of living, in the overall human development progress. Also found is that in China, seriously unbalanced developments have been found among the three aspects of human development, and the overall regional disparities of China have being increasingly attributed to regional economic disparities. The key to eliminate the unbalanced developments is to emphasize more on the role of government in public service delivery, and facilitate government transition towards service orientation.