Improved Class of Regression Type Mean Estimators in Simple Random Sampling Using Concomitant Variable: An Application in T-20 International Cricket

This is the authors' abstract. We don't add key points for this paper.

In sample surveys, the information on supplementary variables is usually used to improve the efficiency of the estimators. The ratio, product, and regression estimators are examples. This study proposes new regression estimators for population mean estimation under simple random sampling using the data of Twenty20 (T-20) International Cricket. The estimators are proposed with the help of non-conventional location parameters of concomitant variable which includes Tri-Mean, Mid-Range, and coefficient of quartile deviation. The bias and mean squared error (MSE) of new estimators have been theoretically derived up to the first-order approximation. The theoretical findings were then compared with the existing estimators numerically through simulation study and real-life data. The numerical results reveal that the suggested estimators are more efficient than the estimators in the literature in all conditions.