数量特征敏感问题的整群抽样调查方法研究及应用  

Cluster Sampling and its Application on Quantitative Sensitive Questions

作　　者：王冕[1] 高歌[1] 

机构地区：[1]苏州大学公共卫生学院流行病与卫生统计教研室,215123

出　　处：《中国卫生统计》2008年第6期586-589,共4页Chinese Journal of Health Statistics

基　　金：国家自然科学基金项目(项目编号:30571620)

摘　　要：目的寻求在整群抽样下,数量特征敏感问题的科学调查方法及相应统计计算公式。方法采用数量特征敏感问题无关联、加法、乘法三种随机应答技术(RRT),整群抽样调查方法,均值的性质、经典的抽样理论等概率统计理论和方法,重测信度、和谐信度评价方法。结果分别推导出三种RRT在整群抽样下,总体均值估计量及其方差的计算公式;成功应用这三种调查方法及相关公式调查得苏州大学近两个学期学生考试作弊平均次数分别为1.1050、1.0375、0.9964,两次重测信度、三种RRT和谐信度的相关系数均大于0.94,P<0.01。结论数量特征敏感问题三种RRT整群抽样调查方法及相应统计计算公式科学可行。Objective To explore scientific methods and corre-sponding formulas for quantitative sensitive questions survey with the sampie selected by cluster sampling. Methods Cluster sampling was applied to three RRT models. Properties of the mean and classic sampling theories were also used. In addition test-retest reliability and congruence reliability were used to evaluate our methods. Results We deduced formulas to calculate the estimator of the population mean of college students who were cheated in exams by cluster sampling. The results got by three RRT models were 1.1050, 1.0375, 0.9964, respectively, with high test-retest reliability and congruence reliability. （correlation coefficient exceeded 0.94 and P〈0.01）. Conclusion The methods and corresponding formulas on quantitative sensitive questions survey with the sample selected by cluster sampling were feasible.

关 键 词：数量特征敏感问题 随机应答技术 整群抽样 考试作弊 

分 类 号：R195[医药卫生—卫生统计学]