Parametric Estimation For The Scale Parameter For Scale Distributions By Moving Extremes Ranked Set Sampling

In this paper, we study A modification of ranked set sampling (RSS) called moving extremes ranked set sampling (MERSS) is considered parametrically, for the estimation of scale parameter of scale distributions. A maximum likelihood estimator (MLE) is considered and its properties are studied under MERSS. It efficiency with respect to the corresponding estimator based on simple random sampling (SRS) is compared for the case of normal dis-tribution. Numerical comparison appears that the estimator can be real competitor to the MLE using (SRS). While its efficiency is slightly inferior than RSS, the former is easier to use than the usual RSS procedure and allows for an increase of set size without introducing too much ranking error.