Abstract

Missingness or incompleteness of data is a challenge to the survey statisticians in producing the reliable estimates of the desired population parameters. If the missingness pattern is unidentifiable, this is the case of random non-response and to deal with such situations, this work proposes some alternative imputations methods to cope with the missing data. The proposed imputation methods result in some efficient estimation procedures of the current population mean in two-occasion successive sampling. The properties of the resultant estimation procedures have been examined and supplemented with empirical studies. Results have been critically analyzed, and recommendations are made to the survey practitioners.

摘要

数据缺失或不完整对调查统计人员产生所需人口参数的可靠估计是一个挑战。如果缺失模式无法识别，这就是随机不响应的情况，为了处理这种情况，这项工作提出了一些替代插补方法来处理缺失数据。所提出的插补方法导致在两次连续抽样中对当前总体均值进行一些有效的估计程序。由此产生的估计程序的特性已经过检验，并辅以实证研究。对结果进行了批判性分析，并向调查从业人员提出了建议。