我国地方政府绩效评估指标数据仓库的代表性对象选取和构建——以江苏四市为研究点

在中国这样的大国,各个地区之间在自然、地理、历史、社会等很多方面千差万别,由于这种异质性的存在,地方政府绩效评估指标的设计是一项噪音很多的系统工程,利用数据挖掘技术建设绩效指标数据仓库并进行挖掘可以有效解决这种异质性问题。论文首先通过标准比的形式,探讨了如何在我国筛选研究对象问题,然后通过将数据挖掘引入政府绩效评估指标设计研究,并以Microsoft SQL Server 2005作为数据挖掘软件,以江苏四市(苏州、南京、盐城、徐州)作为研究对象,在处理国家统计年鉴、地方统计年鉴、部门统计年鉴、政府及其各部门的工作计划与方案、工作记录等海量信息的基础上建立了四市的数据仓库,为进一步进行指标挖掘打下了基础。

Choosing the Data Mining Represent Objects in China’s Local Governments and Establish the Data Warehouses of the Objects: A Study in the Four municipal Governments in Jiangsu Province

In a tremendously large country like China,there are substantial differences on natural geographic features,history background,and social realities among the varied regions.Because of the heterogeneity,the local government performance evaluation indicator designing is a systematical engineering which could be affected by various factors.In this paper,we use the "standard proportion" to develop a new way to choose the study objects among the great many governments of varied level in China.As the study objects chosen,we take advantage of the DM tool of Microsoft SQL Server 2005 to establish a government performance evaluation indictor data warehouse of the four municipal governments in Jiangsu Province by processing the data of National Statistical Yearbook,Local Statistical Yearbook,Sector Statistics Yearbook,government departments’ work plans & programs,etc.