Efficient Ratio Type Estimators of Population Variance through Linear Transformation in Simple and Stratified Random Sampling

In this article, we haveproposed a ratio-type estimator of population variance by taking new transformation on known extreme population values of auxiliary variable,for the simple random sampling (SRS) technique. We have expandedthe proposed estimator from simple random sampling to stratified random sampling and proposed combined estimator. The expressions for biases and mean square errors(MSEs), up to first order of approximation have been obtained for SRS, whereas for stratified random sampling only expression for MSE have been derived. In comparison, proposed estimators are found to perform better than the other existing estimators of similar type. An empirical study has been carried out to show the superiority of the proposed estimators and techniques.