Two-layer ranked set sampling with concomitant variables

Abstract

The notion of ranked set sampling (RSS) proposed by McIntyre (Aust. J. Agri. Res. 3 (1952) 385) provides a methodology for developing efficient sampling schemes. In many practical problems, the variable of interest is costly to measure but is associated with several easily obtainable concomitant variables. In this article, we apply the idea of RSS and develop a sampling scheme which is referred to as the two-layer RSS by using concomitant variables. The properties of the two-layer RSS are investigated and compared with those of other competitive sampling schemes. Some simulation studies are given. The two-layer RSS provides an useful tool to achieve observational economy. It has potential applications in areas such as environmental and ecological studies, population survey, and medical studies, etc. © 2002 Elsevier Science B.V. All rights reserved.