AN ALTERNATIVE FAMILY OF ESTIMATORS FOR POPULATION MEAN IN PRESENCE OF NON-RESPONSE WHEN THE POPULATION MEAN OF AUXILIARY CHARACTER IS NOT KNOWN

摘要

This paper considers the problem of estimating the population mean Y of the study variate y in the situation when information on the study variate y is not available for the initial sample while information on the auxiliary variable x is available for initial sample (i.e. complete sample) but the population mean X of the auxiliary character is not known. A family of estimators for Y has been suggested and its properties are studied. Usual unbiased estimator, ratio, product and difference type estimators are identified as members of the proposed family. Realistic conditions are obtained in which the proposed family is better than conventional estimators. Optimum sampling and sub sampling aspects are given. For illustration an empirical study is carried out to demonstrate the performance of various estimators.