概率抽样条件下样本代表性事后评估方法探讨.pdf

第 29 卷第 7 期统计研究 Vol. 29,No. 7
2012 年 7 月 Statistical Research Jul. 2012
概率抽样条件下样本代表性
事后评估方法探讨*
宋子轩冷燮陈瑶瑶
内容提要样本代表性直接牵涉到统计数据质量和统计公布引起的民众反响,目前社会上不乏对政府统计数
, ,
据的质疑之声最终影响到政府统计机关的公信力因此有必要重新审视现行样本代表性的研究。目前相关文献
普遍强调不同抽样方式下的样本代表性的相对性内涵,确保样本的代表性仅从抽样方法和样本量两个维度入手,
,
缺乏对既定抽样方法下样本代表性的事后评估体系的探索以及多样本之间样本代表性优劣的比较方法研究。鉴
,
于此本文在结合人口普查数据基础上尝试从样本—总体整体分布和内部属性结构两个方面构建样本代表性事后
,
评估的一整套指标和假设检验进而找到一种多样本代表性比较的依据。最后对浦东新区 2010 年城镇居民收入
调查样本进行了代表性检验的尝试。
关键词抽样样本代表性事后评估分布检验列联系数

中图分类号 C811 文献标识码 A 文章编号 1002 - 4565 2012 07 - 0096 - 05
Discussions on the Post-Evaluation of Sample’s Representativeness
in the Condition of Probability Sampling
Song Zixuan Leng Xie Chen Yaoyao
,
Abstract The sample’s representativeness directly involves the quality of statistics and its public repressiveness but
, ,
nowadays sound of doubts arises frequently which further influences the credibility of governmental statistical offices so it’
s necessary to reconsider the research on the sample’s representativeness. The current related literature has always been
,
focused on its relativity between different sampling methods to guarantee the sample’s representativeness generally set an
,
emphasis on the sampling design and sample size which lacks the research on post-evaluation of sample ’s
representativeness under the given sampling method and parable methods of multiple sam