两阶段RDD方法无回答的影响及其改进  

Influence and Improvement of Non-Response in Two-Stage RDD Method

作　　者：李锋[1] Li Feng(School of Statistics,Capital University of Economics and Business,Beijing 100070,China)

机构地区：[1]首都经济贸易大学统计学院

出　　处：《统计与决策》2018年第16期29-31,共3页Statistics & Decision

摘　　要：计算机辅助电话调查应用日益普遍,在住户调查中为了提高住户的比例,发展了Mitofsky-Waks-berg两阶段RDD方法。文章分析了在无回答率较高,且初级单元间无回答率差异较大时引起的偏倚,分析偏倚的特点,并且提出一种基于随机组方法的抽样设计,旨在解决计算机辅助调查中的无回答问题及地区间无回答率差异,并且能够得到性能良好的估计量。The application of computer assisted telephone survey is becoming more and more common. In order to improve the proportion of households in household survey, the Mitofsky-Waksberg two-phase RDD method has been developed. This paper analyzes the bias caused by the high non-response rate and the large difference in the non-response rate among the primary sampling units, as well as the characteristics of the bias. And then the paper proposes a sampling design based on the random group method which aims to solve the non-response in computer assisted telephone survey and the difference in the non-response rate among the regions and also be able to get good estimators.

关 键 词：Mitofsky-Waksberg两阶段RDD方法 无回答 随机组 抽样设计 

分 类 号：C811[社会学—统计学]