Abstract
A method is derived for finding the average Spearman rank correlation coefficient ofN sets of ranks with a single dependent or criterion ranking ofn items without computing any of the individual coefficients. Procedures for calculating the exact distribution ofρ av for small values ofN andn are described for the null case. The first four moments about zero of this distribution are derived, and it is concluded that for samples as small asN=4 andn=4 the normal distribution can be used safely in testing the hypothesisρ av=0.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Friedman, Milton. The use of ranks to avoid the assumption of normality implicit in the analysis of variance.J. Amer. statist. Ass., 1937,32, 675–701.
Hotelling, H., and Pabst, M. R. Rank correlation and tests of significance.Ann. math. Statist., 1936,7, 29–43.
Kelley, T. L. Statistical method. New York: The Macmillan Co., 1923.
Kendall, M. G. The advanced theory of statistics, Vol. I, 4th Ed. London: Charles Griffin and Co., 1948.
Kendall, M. G., Kendall, S. F. H., and Babington Smith, B. The distribution of Spearman's coefficient of rank correlation.Biometrika, 1938,30, 251–273.
Kendall, M. G., and Babington Smith, B. The problem ofm rankings.Ann. math. Statist., 1939,10, 275–287.
Kendall, M. G. Rank correlation methods. London: Charles Griffin and Co., 1948.
Spearman, Charles. ‘Footrule’ for measuring correlation.Brit. J. Psychol., 1906,2, 89–108.
Author information
Authors and Affiliations
Additional information
This problem first came to the writer's attention in discussions with Dr. Dean J. Clyde.
Rights and permissions
About this article
Cite this article
Lyerly, S.B. The average spearman rank correlation coefficient. Psychometrika 17, 421–428 (1952). https://doi.org/10.1007/BF02288917
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02288917