A Better Estimator of Population Mean with Power Transformation Based on Ranked Set Sampling

Ranked set sampling (RSS) was first suggested by McIntyre (1952) to increase the efficiency of estimate of the population mean. It has been shown that this method is highly beneficial to the estimation based on simple random sampling (SRS). There has been considerable development and many modifications were done on this method. This paper presents a modified ratio estimator using prior value of coefficient of kurtosis of an auxiliary variable x, with the intention to improve the efficiency of ratio estimator in ranked set sampling. The first order approximation to the bias and mean square error (MSE) of the proposed estimator are obtained. A generalized version of the suggested estimator by applying the Power transformation is also presented.