ON SOME RECENT DEVELOPMENTS IN RANKED SET SAMPLING

Arun K. Sinha
2005 Bulletin of Informatics and Cybernetics  
McIntyre (1952) proposed a cost-effective survey sampling method that is currently known as ranked set sampling (RSS) in the literature. In this method a fairly large number of randomly identified sampling units are partitioned into small subsets of the same size. The units of each subset are ranked separately with respect to the characteristic of interest without obtaining their actual measurements. The information used for this purpose is supposed to be easily available and inexpensive, and
more » ... actly one unit of each subset with a specified rank is quantified. As the ranking induces stratification on the population it provides a more structured sample than a simple random sample does with the same size. This sample, in turn, yields more efficient estimators of many parameters of interest than a simple random sample of the same size does. Moreover, its implementation needs only the ranking of the randomly selected units, which does not depend upon the method employed for determining the ranking. Thus, one can use any or all the available information (in absence of actual quantification) including subjective judgment for the purpose. Interestingly, by taking advantage of the experience and expertise of the field personnel it exploits the auxiliary information that is not effectively utilized by standard probability survey sampling designs. Even in the presence of ranking error it provides unbiased and more efficient estimators of various population parameters. It has been successfully used in the several areas on interest. Recently, it has been used under the parametric setting for estimating the parameters of several known distributions. This paper discusses its theory, methods and applications. Apart from McIntyre's method of ranked set sampling (MRSS) there are some more RSS methods. In this paper we also discuss them with some newly developed estimators. This work may be of particular interest for those who have been looking for a cost-effective survey sampling technique.
doi:10.5109/12596 fatcat:jugvjzdxirhkncceqpyry5cboq