In testing the hypothesis that the variances of two populations are equal, a test based on the ration F' of the ranges of two samples, one from each population, is simpler than the conventional F test based on the ratio of the sample variances, and it is only alightly less powerful. Table 1 gives percentage points of the ratio of the rangers of two samples from a normal population which are more extensive and more accurate than any previously published. Table 2 compares the power of the F' test with that of the F test. A description of the method of computation is given.
No takes yet. Share an insight, caveat, or question.
H. Leon Harter (1963) studied this question.