Abstract
A new method of sampling is described. Take the largest in the first of n sets, each of 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.