Estimation Of The Median Under Ranked Set Sampling

Sampling survey is an important way to collect the data. McIntyre (1952) pro-posed the ranked set sampling (RSS) to solve the practical problems.Based on RSS, a lot of new ranked set sampling methods were developed, such as extreme ranked set sampling (ERSS),median ranked set sampling (MRSS),robust extreme ranked set sampling (RERSS) and robust extreme ranked set sampling (DRERSS).This paper mainly discusses the efficiency of the population median estimation under the aforementioned RSS.Considering the specialty of the sampling methods used, the traditional median estimation method under SRS may not work very well. This paper proposes two new estimation methods based on the population median esti-mation methods under different samplings mentioned above. And the Monte Carlo simulation method is used to evaluate the efficiency of population median which is estimated by different estimation methods under several ranked set sampling meth-ods. The simulation results demonstrate the effectiveness of the proposed methods in symmetrical distributions and some of the asymmetric distributions.