A GENERAL PROCEDURE FOR ESTIMATING THE MEAN OF A SENSITIVE VARIABLE USING AUXILIARY INFORMATION

Abstract

This paper proposes classes of estimators for the mean of sensitive variable utilizing information on a non – sensitive auxiliary variable. Expressions for the biases and mean square errors of the suggested estimators correct up to first order of approximation are derived. It has been shown that the suggested new class of estimators based on the known population meanX and variance Sx2 of the auxiliary variable X are better than conventional unbiased estimators which do not utilize the auxiliary information, Sousa et al.’s (2010) ratio estimator and Gupta et al.’s (2012) regression estimator under a very realistic condition.