数量特征敏感问题分层两阶段整群抽样的统计方法  

Stratified two-stage cluster sampling on unrelated question model for quantitative sensitive questions

作　　者：朱宏儒[1] 高歌[1] 于明润[1] 王冕[1] 贺志龙[1] 李旭东[1] 

机构地区：[1]苏州大学公共卫生学院卫生统计教研室,江苏苏州215123

出　　处：《南京医科大学学报（自然科学版）》2009年第6期909-912,共4页Journal of Nanjing Medical University(Natural Sciences)

基　　金：国家自然科学基金资助项目(30571620)

摘　　要：目的:寻求在分层两阶段整群抽样下,数量特征敏感问题的科学调查方法及相应统计公式。方法:数量特征敏感问题无关联随机应答技术(RRT)模型,分层两阶段整群抽样调查方法,均值的性质、抽样理论等统计理论和方法被使用。结果:推导出无关联RRT模型在分层两阶段整群抽样下,总体均值估计量及其估计方差的计算公式;成功应用该方法及相关公式调查得苏州大学学生近两个学期考试作弊平均次数为1.0348。结论:数量特征敏感问题无关联RRT模型分层两阶段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 method and corresponding formulas for quantitative sensitive questions survey with the sample selected by stratified two-stage cluster sampling. Methods：Stratified two-stage cluster sampling,unrelated question RRT model, sampling theories, properties of mean were used. Results：The formulas of the estimator of the population mean and its variance for sensitive questions on unrelated question RRT model in stratified two-stage cluster sampling were deduced. The survey methods and formulas were employed successfully in a survey of the frequency of cheating in exams among college students at Suzhou University, and the mean of the frequency was 1.034 8. Conclusion：The method and corresponding formulas for sensitive questions on unrelated question RRT model in stratified two-stage cluster sampling were feasible.

关 键 词：敏感问题 随机应答技术 分层两级抽样 作弊 总体均值 

分 类 号：O212.2[理学—概率论与数理统计]