An Improved Combined Estimators for Finite Population Mean in Presence of Measurement Errors

Abstract

This article addresses the problem of estimating the nite population mean in stratied random sampling.
We propose an improved combined class of estimators for estimating the nite population mean. The
expressions for the bias and mean squared error of the proposed estimator are derived up to the rst
order of approximation. The performance of the proposed class of estimators is compared with existing
estimators both theoretically and numerically. It is shown that the proposed class of estimators is more
ecient than the conventional ratio, product and regression estimator suggested by Isaki (1983), Singh
et al. and Grover (2011).