Answers are grounded in this paper and cite their sources.
A new method of sampling is described. Take the largest in the first of n sets, each of the n random items, the second largest in the second set, and so on to the smallest in the nth set. The sample of n items selected in this way is an unbiased sample of the population. For typical unimodal distributions the mean of such a sample is slightly less than(n + 1)/2 times more efficient than the mean of n items taken at random. The application of the ranked sample method to pasture measurement is discussed.
No takes yet. Share an insight, caveat, or question.
Gary A. McIntyre (2005) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: