Some puzzling results from a computer simulation study are explained by showing that the sample skew coefficient has population‐independent bounds depending only on the sample size. Similar results are obtained for the coefficient of variation of positive data, the maximum standardized deviate, and the standardized range. The upper bounds of these statistics are ( n − 2)/( n − 1) 1/2 , ( n − 1) 1/2 , ( n − 1) 1/2 , and (2n) 1/2 .
No takes yet. Share an insight, caveat, or question.
W. Kirby (1974) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: