Row–Column Sampling Design Using Auxiliary Ranking Variables

Abstract

In this paper, we present a new class of row–column sampling design when a sampling region is presented by non-overlapping quadrats of an rp-by-p row–column grid. Quadrats are rank-ordered on a relevant auxiliary variable, first in the rp rows of the grid and then in the so formed p ranked columns. This ranking enhances the precision of the sampling using ideas from standard rank set sampling methods. The sampling design falls in the traditional sampling framework where the sample selection probabilities are independent of the variables of interest. Selection probabilities are governed by a spatial design and the auxiliary information to facilitate better sampling coverage over the sampling region. The paper constructs unbiased estimators for population mean, total and provides variance estimates for them. It also shows when the new sampling design performs better than its competitors. The new sampling design is applied to a forest and two agricultural field samples to estimate the population means. Supplementary materials accompanying this paper appear online.