Statistical Papers

, Volume 40, Issue 2, pp 159–174 | Cite as

Small-sample comparisons for the Rukhin goodness-of-fit-statistics

  • J. A. Pardo
  • M. C. Pardo
Articles
Received:
Revised:

Abstract

Rukhin's statistic family for goodness-of-fit, under the null hypothesis, has asymptotic chi-squared distribution; however, for small samples the chi-squared approximation in some cases does not well agree with the exact distribution. In this paper we consider this approximation and other three to get appropriate test levels in comparison with the exact level. Moreover, exact power comparisons for several values of the parameter under specified alternatives provide that the classical Pearson's statistic, obtained as a particular case of Rukhin statistic, can be improved by choosing other statistics from the family. An explanation is proposed in terms of the effects of individual cell frequencies on the Rukhin statistic.

AMS 1991 subject classification

Primary 62B10 secondary 62E20 

Key words and phrases

ϕ-divergences Edgeworth expansion second order limit distribution Rukhin's statistic exact power randomized test 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Basu, A. and Sarkar, S. (1994): “On disparity based goodness-of-fit tests for multinomial models”. Stat. and Prob. Letter, 19, 307–312.CrossRefMathSciNetMATHGoogle Scholar
  2. [2]
    Bednarski, T. and Ledwina, T. (1978): “A note on a biasedness of tests of fit”. Mathematische Operationsforschung und Statistik, Series Statistics, 9, 191–193.MathSciNetMATHGoogle Scholar
  3. [3]
    Cohen, A. and Sackrowitz, H.B. (1975): “Unbiasedness of the chi-square, likelihood ratio, and other goodness of fit tests for the equal cell case”. Annals of Statistics, 3, 959–964.CrossRefMathSciNetMATHGoogle Scholar
  4. [4]
    Cressie, N. and Read, T.R.C. (1984): “Multinomial goodness of fit tests”. J. Roy. Statist. Soc., B, 46, 440–464.MathSciNetMATHGoogle Scholar
  5. [5]
    Csiszár, I. (1967): “Information type measures of difference of probability distributions and indirect observations”. Studia Sci. Mat. Hung., 2, 299–318.MATHGoogle Scholar
  6. [6]
    Gil, M.A. (1989): “A note on stratification and gain in precision in estimating diversity from large sample”. Comm. Statist. Theory and Methods, 18, 1521–1526.CrossRefMathSciNetMATHGoogle Scholar
  7. [7]
    Good, I.J. and Smith, E.P. (1985): “The variance and covariance of a generalized index of similarity especially for a generalization of an index of Hellinger and Bhattacharyya”. Comm. Statist. Theory and Methods, 14, 3053–3061.CrossRefGoogle Scholar
  8. [8]
    Greenwood, P. and Nikulin, M.S. (1988): “Application of test of chi-square type”. J. Soviet Math., 43 (6), 2776–2791.CrossRefMathSciNetMATHGoogle Scholar
  9. [9]
    Holst, L. (1972): “Asymptotic normality and efficiency for certain goodness-of-fit tests”. Biometrika, 59 (1), 137–145.CrossRefMathSciNetMATHGoogle Scholar
  10. [10]
    Larntz, K. (1978): “Small-Sample comparisons of Exact Levels for chisquared Goodness-of-fit Statistics”. Journal of the American Statistical Association, 73, 253–263.CrossRefMATHGoogle Scholar
  11. [11]
    Liese, F. and Vajda, I. (1987): Convex Statistical Distances. Teubner, Leipzig.MATHGoogle Scholar
  12. [12]
    Lindsay (1994): “Efficiency versus robustness: The case for minimum Hellinger distance and other methods”. Annals of Statistics, 22, 1081–1114.CrossRefMathSciNetMATHGoogle Scholar
  13. [13]
    Mann, H.B. and Wald, A. (1942): “On the choice of the number of intervals in the application of the chi-square test”. Ann. Math. Statist., 13, 306–317.CrossRefMathSciNetMATHGoogle Scholar
  14. [14]
    Menéndez, M.L., Pardo, J.A., Pardo, L. and Pardo, M.C. (1997a): “Asymptotic approximations for the distribution of the (h, Φ)-divergence goodness-of-fit statistic: Application to Renyi's statistic”. Kybernetes, 26 (4), 442–452.CrossRefMATHGoogle Scholar
  15. [15]
    Menéndez, M.L., Morales, D., Pardo, L. and Vajda, I. (1997b): “Asymptotic distributions of Φ-divergence of hypothetical and observed freqencies on refined partitions”. Statistica Neerlandica (in print).Google Scholar
  16. [16]
    Morales, D., Pardo, L. and Vajda, I. (1995): “Asymptotic divergences of estimates of discrete distributions”. Journal of Statistical Planning and Inference, 48, 347–369.CrossRefMathSciNetMATHGoogle Scholar
  17. [17]
    Morris, C. (1975): “Central limit theorems for multinomial sums”. Annals of Statistics, 3, 165–188.CrossRefMathSciNetGoogle Scholar
  18. [18]
    Nayak, T.K. (1985): “On diversity measures based on entropy functions”. Comm. Statist. Theory and Methods, 14, 203–215.CrossRefMathSciNetMATHGoogle Scholar
  19. [19]
    Pardo, L. Morales, D., Salicrú, M. and Menéndez, M.L. (1993): “The ϕ-divergence statistic in bivariate multinomial populations including stratification”. Metrika, 40, 223–235.CrossRefMathSciNetMATHGoogle Scholar
  20. [20]
    Pardo, M.C. (1994): “On testing independence in multidimensional contingency tables with stratified random sampling”. Information Science, 78, 101–118.CrossRefMathSciNetMATHGoogle Scholar
  21. [21]
    Pardo, M.C. (1995): “Tests of independence for multidimensional contingency tables based on (h, Φ)-divergences measures”. Utilitas Mathematica, 48, 75–91.MathSciNetMATHGoogle Scholar
  22. [22]
    Pardo, M.C. (1996): “An empirical investigation of Cressie and Read tests for the hypothesis of independence in three-way contingency tables”. Kybernetika, 32(2), 175–183.MathSciNetMATHGoogle Scholar
  23. [23]
    Pearson, K. (1900): “On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling”. Philosophy Magazine, 50, 157–172.Google Scholar
  24. [24]
    Rao, C.R. (1965): “Linear Statistical Inference and its Applications”. John Wiley, New York.MATHGoogle Scholar
  25. [25]
    Read, T.R.C. and Cressie, N. (1988): “Goodness of fit Statistics for Discrete Multivariate Data”. Springer Verlag.Google Scholar
  26. [26]
    Rukhin, A.L. (1994): “Optimal estimator for the mixture parameter by the method of moments and information affinity”. Trans. 12th Prague Conference on Information Theory, 214–219.Google Scholar
  27. [27]
    Salicrú, M., Menéndez, M.L., Morales, D. and Pardo, L. (1993): “Asymptotic properties of (r,s)-directed divergence in a stratified sampling”. Applied M Mathematics and Computation, 55, 131–152.CrossRefMATHGoogle Scholar
  28. [28]
    Schorr, B. (1974): “On the choice of the class intervals in the application of the chi-square test”. Math. Operationsforsch. Statist., 5, 357–377.MathSciNetGoogle Scholar
  29. [29]
    Siotani, M. and Fujikoshi, Y. (1984): “Asymptotic approximations for the distributions of multinomial goodness-of-fit tests”. Hiroshima Mathematics Journal 14, 115–124.MathSciNetMATHGoogle Scholar
  30. [30]
    Sturges, H.A. (1926): “The choice of a class interval”. J. Amer. Statist. Assoc., 21, 65–66.Google Scholar
  31. [31]
    Vajda, I. (1989): “Theory of statistical inference and information”. Kluwer Academic Publishers, Dordrecht.MATHGoogle Scholar
  32. [32]
    Yarnold, J. K. (1972): “Asymptotic Approximations for the Probability That a Sum of Lattice Random Vectors Lies in a Convex Set”. Annals of Mathematical Statistics, 43, 1566–1580.CrossRefMathSciNetMATHGoogle Scholar
  33. [33]
    Zografos, K., Ferentinos, K. and Papaioannou, T. (1990): “Φ-divergence statistics: sampling properties and multinomial goodness of fit and divergence tests”. Comm. Statist. Theory and Methods, 19(5), 1785–1802.CrossRefMathSciNetMATHGoogle Scholar
  34. [34]
    Zografos, K. (1992): “Asymptotic properties of Φ-divergence statistic and its applications in contingency tables”. Technical Report 185, Math. Dept., Univ. of Ioannina.Google Scholar

Copyright information

© Springer-Verlag 1999

Authors and Affiliations

  • J. A. Pardo
    • 1
  • M. C. Pardo
    • 1
  1. 1.Department of Statistics & O.R.Complutense University of MadridMadridSpain

Personalised recommendations