New class of estimators of the population mean using the known population median of the study variable (Q2214191)

Summary: In this paper, we propose an improved class of estimators of the population mean using the population median of the study variable. We study the properties of the sampling distribution of the proposed class of estimators up to the approximation of order one. Different values of the two characterising constants in the new estimators affect the mean squared error (MSE) of the proposed family of estimators. Finding the optimum values of the constants to minimise the MSE of the suggested class of estimators provides the least MSE of the recommended family for these optimal values of the characterising scalars. We compare the proposed family of estimators with other competing estimators of the population mean. The theoretical findings are justified with an empirical example and reveal that the proposed class of estimators performs more efficiently than other competing estimators of the population mean under a simple random sampling without replacement (SRSWOR) scheme.