摘要
无回答问题使被调查的数据存在缺失,增加了统计分析的难度.针对存在缺失数据的问题,常用一些插补估计方法,分别运用两种推理方法分析插补估计的偏差和方差以及与方差估计有关的问题.在实际情况中,需要针对不同情况,选择合理的估计模型.
Nonresponse inevitably occurs in most surveys.It makes some but not all the survey variables have missing data and there will be an increase of statistical analysis difficulty.There are a number of interpolation methods used for the problem of missing data.Two kinds of reasoning approaches are applied to analyzed the bias and variance generated by the inerpolating estimation and the related problems with variance estimation.In practice,the reasonable estimation model should be selected for different circumstances.
出处
《华北水利水电学院学报》
2010年第2期98-103,共6页
North China Institute of Water Conservancy and Hydroelectric Power
关键词
无回答模型
缺失数据插补
偏差
方差
Nonresponse Model
interpolation of missing data
bias
variance
