Modified ranked set sampling schemes for estimating the population mean

In this paper, two new sampling schemes called centralized ranked set sampling (CRSS) and systematic ranked set sampling (SRSS) for estimating the population mean are introduced. The performance of the proposed estimators are discussed along with its properties, and it is shown that new sampling schemes generate an unbiased estimator for the population mean. The variance and relative efficiency of the proposed estimators are computed by using the normal, logistic, student't and poisson distributions. On the basis of simulation and empirical results, it is observed that the new sampling schemes are more efficient than usual ranked set sampling (RSS) and simple random sampling (SRS) schemes.