基于二重抽样的权数调整研究  

Research on Weight Adjustment Based on Double Sampling

作　　者：王小宁[1] Wang Xiaoning(School of Data Science and Media Intelligence,Communication University of China,Beijing 100024,China)

机构地区：[1]中国传媒大学数据科学与智能媒体学院,北京100024

出　　处：《统计与决策》2023年第19期41-46,共6页Statistics & Decision

基　　金：国家统计局重点资助项目(2020LZ27);中国传媒大学科研基金资助项目(CUC230B022)。

摘　　要：样本量的确定和分配是抽样设计中的一个重要内容,确定样本量不仅需要综合考虑费用与精度的关系,还需要考虑其所采用的抽样方式。文章采用二重抽样对调查产生的缺失数据进行集中处理,通过对这部分不完整的信息进行有效利用,能够在一定程度上提高调查的精度,并比较了采用二重抽样和不采用二重抽样情况下估计量的标准差,论证了权数的调整方法的有效性,推导出了实际目标估计量的计算公式。在地级市(自治州)层面上,基于与城乡和年龄有关的辅助变量,提出采用迭代法和事后分层相结合的方法,对城乡和不同年龄段样本的权数进行调整,使样本结构与总体结构一致。The determination and allocation of sample size is an important content of sampling design.In order to determine the sample size,it is necessary to consider not only the relationship between cost and accuracy,but also the sampling method ad⁃opted.This paper uses double sampling to centrally process missing data generated in the survey.By effectively utilizing the in⁃complete information,the accuracy of the survey can be improved to a certain extent.The paper also compares the standard devia⁃tion of estimators with double sampling and without double sampling,demonstrates the effectiveness of weight adjustment meth⁃ods,and derives the calculation formula for the actual target estimate.Finally,at the level of prefecture-level cities(autonomous prefectures),and based on auxiliary variables related to urban-rural and age,the paper proposes a combination of iterative meth⁃od and post stratification method to adjust the weights of urban-rural and age group samples,so that the sample structure is con⁃sistent with the overall structure.

关 键 词：分层抽样 二重抽样 样本量 权数调整 

分 类 号：C811[社会学—统计学]