Abstract
This chapter examines measures of association designed for two ordinal-level variables that are based on pairwise comparisons of differences between rank scores. Included in Chap. 5 are Kendall’s τ a and τ b measures of ordinal association, Stuart’s τ c measure, Goodman and Kruskal’s γ measure, Somers’ d yx and d xy measures, Kim’s d y⋅x and d x⋅y measures, Wilson’s e measure, Whitfield’s S measure for an ordinal variable and a binary variable, and Cureton’s rank-biserial correlation coefficient.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Some authors prefer to indicate the number of concordant pairs by P and the number of discordant pairs by Q. Still others indicate the number of concordant pairs by N + and the number of discordant pairs by N −.
- 3.
The number of pairs tied on both variables x and y (T xy) is not used in any of the six measures.
- 4.
There are actually many more than six measures of ordinal association based on pairwise comparisons; only the most common six measures are discussed here.
- 5.
Yule’s Q for 2×2 contingency tables also has S in the numerator and preceded Kendall’s τ a by some 40 years [51, 52]. While Yule’s Q is occasionally prescribed for rank-score data [29, p. 255–256], it was originally designed for categorical data and 2×2 contingency tables; it is therefore described more appropriately in Chap. 9.
- 6.
In general, setting L = 1, 000, 000 ensures a probability value with three decimal places of accuracy [19].
- 7.
- 8.
A summary in English of the Rodrigues 1839 article is available in Mathematics and Social Utopias in France: Olinde Rodrigues and His Times [1, pp. 110–112].
- 9.
This paper was cited by Moran in 1947 as “Rank correlation and a paper by H.G. Haden,” [36, p. 162] but apparently the title was changed at some point to “Rank correlation and permutation distributions” when it was published in Proceedings of the Cambridge Philosophical Society in 1948.
- 10.
Technically, Fig. 5.1 is a permutation graph of a family of line segments that connect two parallel lines in the Euclidean plane. Given a permutation {4, 2, 3, 1, 5} of the positive integers {1, 2, 3, 4, 5}, there exists a vertex for each number {1, 2, 3, 4, 5} and an edge between two numbers where the segments cross in the permutation diagram.
- 11.
In general, L = 1, 000, 000 randomly selected values ensure a probability value with three decimal places of accuracy [19].
- 12.
A number of authors prefer to reserve the symbol gamma (γ) for the population parameter and indicate the sample statistic by the letter G.
- 13.
Coincidentally, in this example analysis the sum of the n 1 = 9 rank scores in Sample B is also 60.
- 14.
Technically, Cureton’s r rb is not considered a measure of correlation [14, p. 629].
References
Askey, R.: The 1839 paper on permutations: Its relation to the Rodrigues formula and further developments. In: Altman, S., Ortiz, E.L. (eds.) Mathematics and Social Utopias in France: Olinde Rodrigues and His Times, Vol. 28. History of Mathematics, pp. 105–118. American Mathematical Society, Providence, RI (2005)
Berry, K.J., Johnston, J.E., Mielke, P.W.: Exact and resampling probability values for measures associated with ordered R by C contingency tables. Psychol. Rep. 99, 231–238 (2006)
Berry, K.J., Johnston, J.E., Mielke, P.W.: A Chronicle of Permutation Statistical Methods: 1920–2000 and Beyond. Springer–Verlag, Cham, CH (2014)
Berry, K.J., Johnston, J.E., Zahran, S., Mielke, P.W.: Stuart’s tau measure of effect size for ordinal variables: Some methodological considerations. Beh. Res. Meth. 41, 1144–1148 (2009)
Berry, K.J., Mielke, P.W.: Assessment of variation in ordinal data. Percept. Motor Skill 74, 63–66 (1992)
Berry, K.J., Mielke, P.W.: Indices of ordinal variation. Percept. Motor Skill 74, 576–578 (1992)
Berry, K.J., Mielke, P.W.: A test of significance for the index of ordinal variation. Percept. Motor Skill 79, 1291–1295 (1994)
Burr, E.J.: The distribution of Kendall’s score S for a pair of tied rankings. Biometrika 47, 151–171 (1960)
Cureton, E.E.: Rank-biserial correlation. Psychometrika 21, 287–290 (1956)
Cureton, E.E.: Rank-biserial correlation when ties are present. Educ. Psychol. Meas. 28, 77–79 (1968)
Durbin, J., Stuart, A.: Inversions and rank correlation coefficients. J. R. Stat. Soc. B Meth. 13, 303–309 (1951)
Festinger, L.: The significance of differences between means without reference to the frequency distribution function. Psychometrika 11, 97–105 (1946)
Galton, F.: Statistics by intercomparison, with remarks on the law of frequency of error. Philos. Mag. 4 49(322), 33–46 (1875)
Glass, G.V.: Note on rank-biserial correlation. Educ. Psychol. Meas. 26, 623–631 (1966)
Goodman, L.A., Kruskal, W.H.: Measures of association for cross classifications. J. Am. Stat. Assoc. 49, 732–764 (1954)
Griffin, H.D.: Graphic computation of tau as a coefficient of disarray. J. Am. Stat. Assoc. 53, 441–447 (1958)
Haden, H.G.: A note on the distribution of the different orderings of n objects. Math. Proc. Cambridge 43, 1–9 (1947)
Hemelrijk, J.: Note on Wilcoxon’s two-sample test when ties are present. Ann. Math. Stat. 23, 133–135 (1952)
Johnston, J.E., Berry, K.J., Mielke, P.W.: Permutation tests: Precision in estimating probability values. Percept. Motor Skill 105, 915–920 (2007)
Jonckheere, A.R.: A distribution-free k-sample test against ordered alternatives. Biometrika 41, 133–145 (1954)
Kendall, M.G.: A new measure of rank correlation. Biometrika 30, 81–93 (1938)
Kendall, M.G.: The treatment of ties in ranking problems. Biometrika 33, 239–251 (1945)
Kendall, M.G.: Rank Correlation Methods. Griffin, London (1948)
Kendall, M.G.: Rank Correlation Methods, 3rd edn. Griffin, London (1962)
Kim, J.-O.: Predictive measures of ordinal association. Am. J. Soc. 76, 891–907 (1971)
Kraft, C.A., van Eeden, C.: A Nonparametric Introduction to Statistics. Macmillan, New York (1968)
Kruskal, W.H.: Historical notes on the Wilcoxon unpaired two-sample test. J. Am. Stat. Assoc. 52, 356–360 (1957)
Leach, C.: Introduction to Statistics: A Nonparametric Approach for the Social Sciences. Wiley, New York (1979)
Loether, H.J., McTavish, D.G.: Descriptive and Inferential Statistics: An Introduction, 4th edn. Allyn and Bacon, Boston (1993)
Mann, H.B.: Nonparametric tests against trend. Econometrica 13, 245–259 (1945)
Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18, 50–60 (1947)
Mielke, P.W., Berry, K.J.: Fisher’s exact probability test for cross-classification tables. Educ. Psychol. Meas. 52, 97–101 (1992)
Mielke, P.W., Berry, K.J.: Permutation Methods: A Distance Function Approach. Springer–Verlag, New York (2001)
Moran, P.A.P.: On the method of paired comparisons. Biometrika 34, 363–365 (1947)
Moran, P.A.P.: Rank correlation and permutation distributions. Math. Proc. Cambridge 44, 142–144 (1948)
Moran, P.A.P.: Recent developments in ranking theory. J. R. Stat. Soc. B Meth. 12, 152–162 (1950)
Moses, L.E.: Statistical theory and research design. Annu. Rev. Psychol. 7, 233–258 (1956)
Newson, R.: Identity of Somers’ D and the rank biserial correlation coefficient (2008). http://www.imperial.ac.uk/nhli/r.newson/miscdocs/ransum1.pdf (2008). Accessed 19 Jan 2016
Porter, T.M.: The Rise of Statistical Thinking, 1820–1900. Princeton University Press, Princeton, NJ (1986)
Randles, R.H., Wolfe, D.A.: Introduction to the Theory of Nonparametric Statistics. Wiley, New York (1979)
Rew, H.: Francis Galton. J. R. Stat. Soc. 85, 293–298 (1922)
Rodrigues, O.: Note sur les inversions, ou dérangements produits dans les permutations (Note on inversions, or products of derangements in permutations). J. Math. Pure. Appl. 4, 236–240 (1839). [The Journal de Mathématiques Pures et Appliquées is also known as the Journal de Liouville]
Sandiford, P.: Educational Psychology. Longmans, Green & Company, New York (1928). [The graphical method appears in an Appendix by S.D. Holmes, ‘A graphical method of estimating R for small groups’, pp. 391–394]
Somers, R.H.: A new asymmetric measure of association for ordinal variables. Am. Sociol. Rev. 27, 799–811 (1962)
Stigler, S.M.: Stigler’s law of eponymy. In: Gieryn, T.F. (ed.) Science and Social Structure: A Festschrift for Robert K. Merton, pp. 147–157. New York Academy of Sciences, New York (1980)
Stuart, A.: The estimation and comparison of strengths of association in contingency tables. Biometrika 40, 105–110 (1953)
Stuart, A.: Spearman-like computation of Kendall’s tau. Brit. J. Math. Stat. Psy. 30, 104–112 (1977)
Whitfield, J.W.: Rank correlation between two variables, one of which is ranked, the other dichotomous. Biometrika 34, 292–296 (1947)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1, 80–83 (1945)
Wilson, T.P.: Measures of association for bivariate ordinal hypotheses. In: Blalock, H.M. (ed.) Measurement in the Social Sciences: Theories and Strategies, pp. 327–342. Aldine, Chicago (1974)
Yule, G.U.: On the association of attributes in statistics: With illustrations from the material childhood society. Philos. T. R. Soc. Lond. 194, 257–319 (1900)
Yule, G.U.: On the methods of measuring association between two attributes. J. R. Stat. Soc. 75, 579–652 (1912). [Originally a paper read before the Royal Statistical Society on 23 April 1912]
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Berry, K.J., Johnston, J.E., Mielke, P.W. (2018). Ordinal-Level Variables, I. In: The Measurement of Association. Springer, Cham. https://doi.org/10.1007/978-3-319-98926-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-98926-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98925-9
Online ISBN: 978-3-319-98926-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)