统计研究 ›› 2019, Vol. 36 ›› Issue (7): 3-12.doi: 10.19343/j.cnki.11-1302/c.2019.07.001

• •    下一篇

政府统计生产体系中的大数据融入探讨——基于数据源与数据质量的分析

黄恒君   

  • 出版日期:2019-07-25 发布日期:2019-07-29

Integrated in Official Statistical Systems—— Based on the Analysis of Data Sources and Data Quality

Huang Hengjun   

  • Online:2019-07-25 Published:2019-07-29

摘要: 大数据在统计生产中潜力巨大,有助于构建高质量的统计生产体系,但符合统计生产目标的数据源特征及其数据质量问题有待明确。本文在寻求大数据源与传统统计数据源共同点的基础上,讨论了统计生产中的大数据源及其数据质量问题,进而探讨了大数据与传统统计生产融合应用。首先从数据生成流程及数据特征两个方面论证并限定了可用于统计生产的大数据源;然后在广义数据质量框架下讨论了大数据统计生产中的数据质量问题,梳理了大数据统计生产流程的数据质量控制要点和质量缺陷;最后根据数据质量分析结果,提出了将大数据融入传统调查的统计体系构建思路。

关键词: 大数据, 政府统计, 统计体系, 数据源, 数据质量

Abstract: Big data have great potential in the statistical production and could be aid to high quality statistical system construction. However, the characteristics of data sources and quality that correspond to the statistical production objectives need to be clarified. On the basis of finding the common points of big data and traditional data sources, this paper discusses the big data sources and its data quality in statistical production, and then discusses the integration of big data and traditional statistical production. An analysis of big data sources available for statistical production is carried out from the aspects of data generation process and data characteristics. Big data quality dimensions in statistical production are analyzed under the generalized data quality framework, and the quality controls and quality defects of the big data statistical production process are pointed out. Finally, a framework of integration of big data with traditional statistical production is also considered.

Key words: Big Data, Official Statistics, Statistical Systems, Data Sources, Data Quality