New double stage ranked set sampling for estimating the population mean

In environmental and many other areas, the main focus of survey is to measure elements using an efficient and cost-effective sampling technique. One way to reach that is by using Ranked set sampling (RSS). RSS is an alternative sampling technique that can be advantageous when measuring the variable of interest is either costly or time-consuming but ranking small sets of units according to the character under investigation by eye or other methods not requiring actual quantifications. The purpose of this article is to introduce a new modification of RSS to estimate the mean of the target population. This proposed technique is a double-stage approach that combines median RSS (MRSS) and MiniMax RSS (MMRSS). The performance of the empirical mean and variance estimators based on the proposed technique are compared with their counterparts in Double RSS (DRSS), Extreme RSS (ERSS), Double Extreme RSS (DERSS), MMRSS, RSS, and simple random sampling (SRS) via Monte Carlo simulation. Simulation results revealed that this new modification is almost always more efficient than their counterparts using MMRSS and SRS, while it is more efficient than RSS in many cases especially when the distribution is asymmetric.