Unbiased estimators of mean, variance and sensitivity level for quantitative characteristics in finite population sampling
Unbiased estimators of mean, variance and sensitivity level for quantitative characteristics in finite population sampling
复制标题
DOI：
10.1007/s00184-009-0234-7
复制
发表时间：
2010-05-01
期刊：
影响因子：
0.7
通讯作者：
Huang, Kuo-Chung
中科院分区：
文献类型：
--
作者：
Huang, Kuo-Chung
本文考虑了在不暴露被调查者身份的情况下获取敏感定量特征的可靠信息的问题。提出了一种广义可选随机响应方法，使我们能够无偏地估计一些未知的总体参数。特别研究了均值、方差和灵敏度水平无偏估计的保证条件。效率比较也进行了研究所提出的程序的性能。
This paper considers the problem of procuring reliable information on sensitive quantitative characteristics without exposing respondents' identities. A generalized optional randomized response procedure is proposed, which enables us to estimate some unknown population parameters unbiasedly. In particular, conditions for the assurance of unbiased estimations of mean, variance and sensitivity level are studied. Efficiency comparisons are also carried out to study the performance of the proposed procedure.