Advertisement

Psychometrika

, Volume 42, Issue 1, pp 111–125 | Cite as

Some exact conditional tests of independence forR ×C cross-classification tables

  • Alan Agresti
  • Dennis Wackerly
Article

Abstract

Exact conditional tests of independence in cross-classification tables are formulated based on theχ2 statistic and statistics with stronger operational interpretations, such as some nominal and ordinal measures of association. Guidelines for the table dimensions and sample sizes for which the tests are economically implemented on a computer are given. Some selected sample sizes and marginal distributions are used in a numerical comparison between the significance levels of the approximate and exact conditional tests based on theχ2 statistic.

Key words

exact test independence contingency tables ordinal and nominal measures of association chi-square test computer algorithm 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agresti, A. The effect of category choice on some ordinal measures of association.Journal of the American Statistical Association, 1976,71, 49–55.Google Scholar
  2. Boulton, D. M. Remark on algorithm 434.Communications of the ACM, 1974,17, 326.Google Scholar
  3. Freeman, G. H. & Halton, J. H. Note on an exact treatment of contingency, goodness of fit and other problems of significance.Biometrika, 1951,38, 141–149.Google Scholar
  4. Goodman, L. A. & Kruskal, W. H. Measures of association for cross classifications.Journal of the American Statistical Association, 1954,49, 732–764.Google Scholar
  5. Goodman, L. A. & Kruskal, W. H. Measures of association for cross classifications III: approximate sampling theory.Journal of the American Statistical Association, 1963,58, 310–364.Google Scholar
  6. Goodman, L. A. & Kruskal, W. H. Measures of association for cross classifications IV: simplification of asymptotic variances.Journal of the American Statistical Association, 1972,67, 415–421.Google Scholar
  7. Haldane, J. B. S. The use ofχ 2 as a test of homogeneity in a (n × 2)-fold table when expectations are small.Biometrika, 1943,33, 234–238.Google Scholar
  8. Halton, J. H. A rigorous derivation of the exact contingency formula.Proceedings of the Cambridge Philosophical Society, 1969,65, 527–530.Google Scholar
  9. Klotz, J. The Wilcoxon, ties, and the computer.Journal of the American Statistical Association, 1966,61, 772–787.Google Scholar
  10. March, D. L. Algorithm 434, exact probabilities forr ×c contingency tables.Communications of the ACM, 1972,15, 991–992.Google Scholar
  11. Nass, C. A. G. The chi-square test for small expectations in contingency tables, with special reference to accidents and absenteeism.Biometrika, 1959,46, 365–385.Google Scholar
  12. Proctor, C. H. Relative efficiencies of some measures of association for ordered two-way contingency tables under varying intervalness of measurement error.Proceedings of the Social Statistics Section, American Statistical Association, 1973, 372–379.Google Scholar
  13. Radlow, R. & Alf, E. Jr. An alternate multinomial assessment of the accuracy of theχ 2 test of goodness of fit.Journal of the American Statistical Association, 1975,70, 811–813.Google Scholar
  14. Roscoe, J. T. & Byars, J. A. An investigation of the restraints with respect to sample size commonly imposed on the use of the chi-square statistic.Journal of the American Statistical Association, 1971,66, 755–759.Google Scholar
  15. Rosenthal, I. Distribution of the sample version of the measure of association, gamma.Journal of the American Statistical Association, 1966,61, 440–453.Google Scholar

Copyright information

© Psychometric Society 1977

Authors and Affiliations

  • Alan Agresti
    • 1
  • Dennis Wackerly
    • 1
  1. 1.Department of Statistics, Nuclear Sciences CenterUniversity of FloridaGainesville

Personalised recommendations