论双系统估计量的无偏性  

Discussing Unbiasedness of Dual System Estimator

作　　者：丁杨[1] 陈新华[2] 杜艾卿 胡桂华[3] DING Yang CHEN Xin-hua DU Ai-qing HU Gui-hua(Propaganda Departmnet, Chongqing Technology and Business University, Chongqing 400067 China School of Information and Statistics, Guangxi University of Finance and Economics, Guangxi Nanning 530003, China School of Math and Statistics, Chongqing Technology and Business University, Chongqing 400067, China)

机构地区：[1]重庆工商大学宣传部,重庆400067 [2]广西财经学院信息与统计学院,广西南宁530003 [3]重庆工商大学数学与统计学院,重庆400067

出　　处：《数理统计与管理》2017年第2期243-252,共10页Journal of Applied Statistics and Management

基　　金：国家社科基金一般项目(15BTJ011)

摘　　要：人口普查质量评估中所使用的双系统估计量是否为无偏估计量是一个很值得深入讨论的问题。只有无偏,才能确保使用双系统估计量估计的目标总体实际人数及人口普查净误差平均等于它们的实际数。针对人口普查质量评估工作中所使用的双系统估计量,论证这个估计量的无偏性条件。采用从既定假设出发进行推演的路径论证。研究结果表明,双系统估计量是目标总体实际人数无偏估计量的必要但非充分的条件是,人口普查与其质量评估调查相互独立以及目标总体中的每一个人在人口普查中的登记概率相同,在质量评估调查中登记的概率也相同。Whether dual system estimator used in census quality assessment is an unbiased estimator is a very worthy of further discussion.Only unbiased,can we ensure population true count and census net error estimated by dual system estimator equal to their true count on average.Against the dual system estimator used in census quality assessment,proving unbiased conditions of the estimator.The path from a given hypothesis to deduction is used to prove.The results show that necessary but not sufficient condition that dual system estimator becomes unbiased estimator of target universe true population is independent between census and its quality assessment survey,and everyone in the universe has the same probability of being registered in the census or quality assessment survey.

关 键 词：人口普查 人口普查质量评估调查 捕获-再捕获模型 双系统估计量 

分 类 号：O212[理学—概率论与数理统计]