Estimation of Population Mean Using Imputation Methods for Missing Data Under Two-Phase Sampling Design

This manuscript emphasizes the estimation procedure of population mean in two-phase sampling when non-response occurs during survey in both phases of sample data. To cope with the problem of missing data, some new imputation methods have been suggested for estimating the population mean which utilize the information on two auxiliary variables. The properties of the resultant estimators are studied which are followed by empirical and simulation studies accomplished on real as well as on artificial data sets which justify the suggested imputation methods. Results are significantly analyzed, and appropriate suggestions are made to the survey practitioners.