一个可供选择的全随机化模型

An Alternative Full Randomized Response Model

构造了一个数量型全随机化模型,它是由被调查者根据自己的意愿从2种选项中选择自己的编码方法,从而增加被调查者对调查的信心,进而增加数据的可靠性;给出了对敏感参数的无偏估计量,以及估计量的方差以及方差的估计。最后对构造的新模型与已有的模型,在精度与保护度方面进行了比较,说明了各自的优缺点;提出了除了精度及保护度外,还应该有刻画被调查者参与程度的一个指标。

A full randomized response model for quantitative sensitive question is constructed in this paper.The strategy is that the respondents can decide the coding methods by their own will from two choices,so as to increase the confidence of the respondents in the investigation,further more to increase the reliability of the data from the respondents.An unbiased estimators of the sensitive parameters,the variance of the estimator and its estimation are given.Finally,a comparison of accuracy and pretection degree is made between the constructed and the existing models.It is suggested that,in addition to the accuracy and protection degree,there should be an index to describe the participation degree of the respondents.