Psychometrika

, Volume 16, Issue 2, pp 207–218 | Cite as

Remarks on the method of paired comparisons: III. A test of significance for paired comparisons when equal standard deviations and equal correlations are assumed

  • Frederick Mosteller
Article

Abstract

A test of goodness of fit is developed for Thurstone's method of paired comparisons, Case V. The test involves the computation of\(\chi ^2 = n\Sigma (\theta '' - \theta ')^2 /821,\), wheren is the number of observations per pair, andθ″ andθ′ are the angles obtained by applying the inverse sine transformation to the fitted and the observed proportions respectively. The number of degrees of freedom is (k−1) (k−2)/2.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bartlett, M. S. The square root transformation in analysis of variance.Suppl. J. roy. stat. Soc., 1936,3, 68–78.Google Scholar
  2. 2.
    Bartlett, M. S. The use of transformations.Biometrics Bull., 1947,3, 39–52.Google Scholar
  3. 3.
    Bliss, C. I. Plant protection, No. 12. Leningrad, 1937.Google Scholar
  4. 4.
    Fisher, R. A. On the dominance ratio.Proc. roy. soc. Edinb., 1922,42, 321–341.Google Scholar
  5. 5.
    Mosteller, F. Remarks on the method of paired comparisons: I. The least squares solution assuming equal standard deviations and equal correlations.Psychometrika, 1951,16, 3–9.Google Scholar
  6. 6.
    Mosteller, F. Remarks on the method of paired comparisons: II. The effect of an aberrant standard deviation when equal standard deviations and equal correlations are assumed.Psychometrika, 1951,16, 203–206.Google Scholar
  7. 7.
    Mosteller, F, and Tukey, J. W. The uses and usefulness of binomial probability paper.J. Amer. statist. Ass., 1949,44, 174–212.Google Scholar
  8. 8.
    Statistical Research Group, Columbia University. Selected techniques of statistical analysis. New York: McGraw-Hill Book Co., 1947.Google Scholar

Copyright information

© Psychometric Society 1951

Authors and Affiliations

  • Frederick Mosteller
    • 1
  1. 1.Harvard UniversityUSA

Personalised recommendations