Purpose: To propose a randomized minima-maxima nomination (RMMN) sampling design for finite population. Summary: Consider a sampling scheme in which a single observation is obtained from a set of randomly chosen subsamples may be of different sizes from a finite population. The observation from a particular sample is maximum or minimum with respect to the attribute of interest and this sampling design is called RMMN sampling design minima-maxima nomination sampling plan was introduced by WiIIemain (Ref. 1) to observe either the maximum contributing element or minimum contributing element for hospitals where the actual expenditure against reimbursed amount is studied. Some studies have been proposed on RMMN sampling such as estimating the distribution function, quantile estimation and control charting for infinite population. This paper introduces randomized minima-maxima nomination sampling design for finite population and shows that strict minima-maxima sampling may not be necessary for the optimum choice.
展开▼