Advertisement

Bivariate Dependence Orderings for Unordered Categorical Variables

  • A. Giovagnoli
  • J. Marzialetti
  • H. P. Wynn
Part of the Springer Optimization and Its Applications book series (SOIA, volume 28)

Summary

Interest in assessing the degree of association between two or more random variables has a long history in the statistical literature. Rather than measuring association, we want ways of comparing it. Restricting the attention in this chapter to unordered categorical random variables, we point at some possible definitions of dependence orderings which employ matrix theory and, to a lesser extent, group theory. This approach allows a unified investigation of the most common indicators in the statistical literature.

One very special type of association is the amount of agreement among different observers that classify the same group of statistical units: in the medical field this has led to widespread use of Cohen's Kappa. Starting with an axiomatic definition of agreement, we show its formal properties. Some criticism of Cohen's Kappa and other measures of agreement in use will ensue.

Keywords

Order Relation Statistical Unit Permutation Matrix Stochastic Matrix Interrater Agreement 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Armitage, P., Blendis, L.M., Smyllie, H.C. (1966). The measurement of observer disagreement in the recording of signs. Journal of the Royal Statistical Society A, 129, 98–109.CrossRefMathSciNetGoogle Scholar
  2. Banerjee, M., Capozzoli, M., McSweeney, L., Sinha, D. (1999). Beyond kappa: A review of interrater agreement measures. The Canadian Journal of Statistics, 27, (1)3–23.MATHCrossRefMathSciNetGoogle Scholar
  3. Bickel, P.J. Lehmann, E.L. (1975). Descriptive statistics for non-parametric models. i: Introduction. The Annals of Statistics, 3, 1038–1044.MATHCrossRefMathSciNetGoogle Scholar
  4. Bishop, Y.M.M., Fienberg, S.E., Holland, P.W. (1975). Discrete multivariate analyses: Theory and practice. MIT Press, Cambridge, MA.MATHGoogle Scholar
  5. Cifarelli, D.M. Regazzini, E. (1986). Concentration function and its role in descriptive statistics. Proceedings of the 33rd Scientific Meeting of the Italian Statistical Society, 2, 347–352.Google Scholar
  6. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37–46.CrossRefGoogle Scholar
  7. Davies, M. Fleiss, J. (1982). Measuring agreement for multinomial data. Biometrics, 38, 1047–1051.MATHCrossRefGoogle Scholar
  8. Farewell, V.T. Sprott, D.A. (1999). Conditional inference for predictive agreement. Statistics in Medicine, 18, 1435–1449.CrossRefGoogle Scholar
  9. Fleiss, J.L. (1971). Measuring nominal scale agreement among many raters. Psychological Bulletin, 76, 378–381.CrossRefGoogle Scholar
  10. Forcina, A. Giovagnoli, A. (1987). Mathematical properties of cross-classification matrices. Bollettino Unione Matematica Italiana, VII(1-B), (2)523–544.MathSciNetGoogle Scholar
  11. Giovagnoli, A. (2002a). Differenti aspetti della connessione: un approccio attraverso la teoria degli ordinamenti. In Studi in onore di Angelo Zanella. Ed. Vita e Pensiero, 329–334.Google Scholar
  12. Giovagnoli, A. (2002b). Stochastic orderings and their use in statistics: the case of association between two variables. In Proceedings of the XLI Scientific Meeting of the Italian Statistical Society, 5–7 June 2002, Milan, 95–104.Google Scholar
  13. Giovagnoli, A. Wynn, H.P. (1985). G-majorization with applications to matrix orderings. Linear Algebra and its Applications, 67, 111–135.MATHCrossRefMathSciNetGoogle Scholar
  14. Giovagnoli, A., Marzialetti, J., and Wynn, H.P. (2006). A new approach to inter-rater agreement through stochastic orderings: the discrete case. Manuscript.Google Scholar
  15. Goodman, L.A. Kruskal, W.H. (1954). Measures of association for cross classifications. Journal of the American Statistical Association, 49, 732–764.MATHCrossRefGoogle Scholar
  16. Goodman, L.A. Kruskal, W.H. (1979). Measures of association for cross classification. Springer-Verlag, New York.Google Scholar
  17. Joe, H. (1985). An ordering of dependence for contingency tables. Linear Algebra and its Applications, 70, 89–103.MATHCrossRefMathSciNetGoogle Scholar
  18. Joe, H. (1997). Multivariate models and dependence concepts. Chapman & Hall, London.MATHGoogle Scholar
  19. Marshall, A.W. Olkin, I. (1979). Inequalities: Theory of Majorization and Its Applications. Academic Press, London.MATHGoogle Scholar
  20. Marzialetti, J. (2006). Lo Studio dell'Agreement mediante gli Ordinamenti. Ph.D. thesis, Department of Statistical Sciences, University of Bologna.Google Scholar
  21. Müller, A. Stoyan, D. (2002). Comparison Methods for Stochastic Models and Risks. Wiley, London.MATHGoogle Scholar
  22. Rogot, E. Goldberg, I.D. (1966). A proposed index for measuring agreement in test-retest studies. Journal of Chronical Disease, 19, 991–1006.CrossRefGoogle Scholar
  23. Ross, S. (1995). Stochastic Processes. Wiley, London.Google Scholar
  24. Scarsini, M. (1991). An ordering of dependence. In Topics in Statistical Dependence, pages 403–414. Block, H.W., Sampson A.R., Savits, T.H. eds, Institute of Mathematical Statistics (Hayward).Google Scholar
  25. Shaked, M. Shanthikumar, J.G. (1994). Stochastic Orders and their Applications. Academic Press, New York, London.MATHGoogle Scholar
  26. Shoukri, M.M. (2004). Measures of Interobserver Agreement. Chapman & Hall, Boca Raton.Google Scholar

Copyright information

© Springer Science+Business Media LLC 2009

Authors and Affiliations

  1. 1.Department of Statistical Sciences, University of Bologna BolognaItaly
  2. 2.Department of Statistical Sciences, University of BolognaBolognaItaly
  3. 3.London School of Economics and Political ScienceLondonUK

Personalised recommendations