Measures of Association for Cross Classifications III: Approximate Sampling Theory
The population measures of association for cross classifications, discussed in the authors’ prior publications, have sample analogues that are approximately normally distributed for large samples. (Some qualifications and restrictions are necessary.) These large sample normal distributions with their associated standard errors, are derived for various measures of association and various methods of sampling. It is explained how the large sample normality may be used to test hypotheses about the measures and about differences between them, and to construct corresponding confidence intervals. Numerical results are given about the adequacy of the large sample normal approximations. In order to facilitate extension of the large sample results to other measures of association, and to other modes of sampling, than those treated here, the basic manipulative tools of large sample theory are explained and illustrated.
KeywordsCovariance Expense Rosen Estima Summing
Unable to display preview. Download preview PDF.
- Hoeffding, Wassily, “An upper bound for the variance of Kendall’s ‘tau’ and of related statistics,” pp. 258–64 in Contributions to Probability and Statistics. Essays in Honor of Harold Hotelling, edited by Ingram Olkin and others, Stanford University Press, Stanford, 1960.Google Scholar
- Kondo, Tsutomu, “On the standard error of the mean square contingency,” Biometrika, 21 (1929), 377–428.Google Scholar
- Kozelka, Robert M., “On some special order statistics from the multinomial distribution,” Unpublished Ph.D. dissertation, Harvard University, 1952.Google Scholar
- Pearson, Karl, “On the probable error of a coefficient of mean square contingency,” Biometrika, 10 (1915), 570–3.Google Scholar
- Sneyers, R., “Remarques à propos d’une généralisation de l’indice de similitude de M. Bouët,” Archiv fÜr Meteorologie, Geophysik und Bioklimatologie, Series A: Meteorologie und Geophysik, Band 11, 1. Heft, 1959, 126–35.Google Scholar