An Adjusted General Family of Population Mean Estimators in the Presence of Non-response under Two-phase Sampling without Known Population Mean of Auxiliary Variable

In this paper, a new family of estimators to estimate population means of a study variable has been proposed under two situations; non-response occurrence in a study variable only and non-response occurrence in both the study and auxiliary variables under two-phase sampling. We assumed that the population mean of an auxiliary variable is unknown. We derive the bias and mean square error of the proposed estimators up to a first order approximation. An empirical study of the proposed estimators shows that they perform better than other existing estimators in terms of a percentage relative efficiency.