Smoothing of Estimators of Population mean using Calibration Technique with Sample Errors

The challenges bedeviling the performance of estimators of population parameters in survey samples as a result of measurement and nonresponse errors are of great concern to researchers and users of statistics. This study suggests new estimators and adopts the calibration approach in smoothing the existing and proposed estimators for optimal performance. We have proposed improved estimators for estimating the finite population mean under stratified random sampling in three different situations: first, the properties of the estimators are considered under nonresponse, then the study of the estimators for measurement errors and in the last case, the estimators are examined in the presence of both measurement and nonresponse errors simultaneously. Expressions for mean square errors are obtained for the suggested estimators. Empirical study has been carried out with two real datasets to validate the theoretical underpinnings of this study.