Skip to main content
SpringerLink
Log in

Bayesian estimation methods for contingency tables

  • Published:
Journal of the Italian Statistical Society Aims and scope Submit manuscript

Summary

A method of inputting prior opinion in contingency tables is described. The method can be used to incorporate beliefs of independence or symmetry but extensions are straightforward. Logistic normal distributions that express such beliefs are used as priors of the cell probabilities and posterior estimates are derived. Empirical Bayes methods are also discussed and approximate posterior variances are provided. The methods are illustrated by a numerical example.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aitchison, J. (1982), The statistical analysis of compositional data (with discussion),J. R. Statist. Soc. Ser. B, 44, 139–177.

    MATH  MathSciNet  Google Scholar 

  • Aitchison, J. (1985a), Practical Bayesian problems in simplex sample spaces, inProceedings of the second international meeting on Bayesian statistics (J. M. Bernardo, M. H. DeGroot, D. V. Lindley and A. F. M. Smith, eds.), pp. 15–32. Amsterdam: North Holland.

    Google Scholar 

  • Aitchison, J. (1985b), A general class of distributions on the simplex, J. R. Statist. Soc. Ser. B, 47, 136–146.

    MATH  MathSciNet  Google Scholar 

  • Aitchison, J. (1986),The statistical analysis of compositional data, London: Chapman & Hall.

    MATH  Google Scholar 

  • Aitchison, J. andShen, S. M. (1980), Logistic-normal distributions: some properties and uses,Biometrika, 67, 261–272.

    Article  MATH  MathSciNet  Google Scholar 

  • Albert, J. H. (1985), Simultaneous estimation of Poisson means under exchangeable and independence models, J. Statist. Comput. Simulat., 23, 1–14.

    MATH  MathSciNet  Google Scholar 

  • Albert, J. H. (1988), Computational methods using a Bayesian hierarchical generalized linear model,J. Amer. Statist. Assoc., 83, 1037–1044.

    Article  MathSciNet  Google Scholar 

  • Albert, J. H. andGupta, A.K. (1982), Mixture of Dirichlet distributions and estimation in contingency tables,Ann. Statist., 10, 1261–1268.

    MATH  MathSciNet  Google Scholar 

  • Albert, J. H. andGupta, A. K. (1983a), Bayesian estimation methods for 2×2 contingency tables using mixtures of Dirichlet distributions,J. Amer. Statist. Assoc., 78, 708–717.

    Article  MathSciNet  Google Scholar 

  • Albert, J. H. andGupta, A. K. (1983b), Estimation in contingency tables using prior information, J. R. Statist. Soc. Ser. B, 45, 60–69.

    MATH  MathSciNet  Google Scholar 

  • Altham, P. M. E. (1969), Exact Bayesian analysis of 2×2 contingency table and Fisher's “exact” significance test,J. R. Statist. Soc. Ser. B, 31, 261–269.

    MathSciNet  Google Scholar 

  • Bishop, Y. M. M., Fienberg, S. E. andHolland, P. W. (1975),Discrete Multivariate Analysis: Theory and Practice, Cambridge, Mass: The MIT press.

    MATH  Google Scholar 

  • Bloch, D. A. andWatson, G. S. (1967), A Bayesian study of the multinomial distribution,Ann. Math. Statist, 38, 1423–1435.

    MathSciNet  Google Scholar 

  • Crook, J. R. andGood, I. J. (1980), On the application of symmetric Dirichlet distributions and their mixtures to contingency tables, part II,Ann. Statist., 8, 1198–1218.

    MATH  MathSciNet  Google Scholar 

  • Dawid, A. P. (1982), Discussion on “The statistical analysis of compositional data” by J. Aitchison,J. R. Statist. Soc. Ser. B, 44, 139–177.

    Google Scholar 

  • Dempster, A. P., Laird, N. M. andRubin, D. B. (1977), Maximum likelihood from incomplete data via theEM algorithm (with discussion),J. R. Statist. Soc. Ser. B, 39, 1–38.

    MATH  MathSciNet  Google Scholar 

  • Good, I. J. (1976), On the application of symmetric Dirichlet distributions and their mixtures to contingency tables,Ann. Statist. 4, 1159–1189.

    MATH  MathSciNet  Google Scholar 

  • Goutis, C. (1993), Recovering extra-binomial variation,J. Statist. Comput. Simulat., 45, 233–242.

    MATH  Google Scholar 

  • Gupta, A. K., Saleh, A. M. MD. E. andSen, P. K. (1989), Improved estimation in a contingency table: independence structure,J. Amer. Statist. Assoc., 84, 525–532.

    Article  MATH  MathSciNet  Google Scholar 

  • Kass, R. E. andSteffey, D. (1989), Approximate Bayesian inference in conditionally independent hierarchical models (parametric empirical Bayes models),J. Amer. Statist. Assoc., 84, 717–726.

    Article  MathSciNet  Google Scholar 

  • Laird, N. M. (1978), Empirical Bayes estimation for two-way contingency tables,Biometrika, 65, 581–590.

    Article  MATH  MathSciNet  Google Scholar 

  • Leonard, T. (1972), Bayesian methods for binomial data,Biometrika, 59, 581–589.

    Article  MATH  MathSciNet  Google Scholar 

  • Leonard, T. (1973), A Bayesian method for histograms,Biometrika, 60, 297–308.

    MATH  MathSciNet  Google Scholar 

  • Leonard, T. (1975), Bayesian estimation methods for two-way contingency tables,J. R. Statist. Soc. Ser. B, 37, 23–37.

    MATH  MathSciNet  Google Scholar 

  • Leonard, T. andNovick, M. R. (1986), Bayesian full rank marginalization for two-way contingency tables,J. Educ. Statist., 11, 33–56.

    Article  Google Scholar 

  • Lindley, D. V. (1964), The Bayesian analysis of contingency tables,Ann. Math. Statist., 35, 1622–1643.

    MathSciNet  Google Scholar 

  • Lindley, D. V. andSmith, A. F. M. (1972), Bayes estimates for the linear model (with discussion),J. R. Statist. Soc. Ser. B, 34, 1–41.

    MATH  MathSciNet  Google Scholar 

  • McGullagh, P. andNelder, J. A. (1989),Generalized Linear Model, 2 nd edition, London: Chapman & Hall.

    Google Scholar 

  • Morris, C. (1983), Parametric empirical Bayes inference: theory and practice,J. Amer. Statist. Assoc., 78, 47–65.

    Article  MATH  MathSciNet  Google Scholar 

  • Morris, M. (1991), A log-linear modeling framework for selective mixing,Math. Biosci., 107, 349–377.

    Article  Google Scholar 

  • Nazaret, W. A. (1987), Bayesian log liner estimates for three-way contingency tables,Biometrika, 74, 401–410.

    Article  MATH  MathSciNet  Google Scholar 

  • Piegorsch, W. W. andCasella, G. (1990), Empirical Bayes estimation for generalized linear models, Biometrics Unit Technical Report, BU-1067-M, Cornell University.

  • Protter, M. H. andMorrey, C. B. (1977),A First Course in Real Analysis, New York: Springer-Verlag.

    MATH  Google Scholar 

  • Steffey, D. andKass, R. E. (1991), Discussion on “That BLUP is a good thing: the estimation of random effects» by G.K. Robinson,Statist. Sci., 6, 15–51.

    MathSciNet  Google Scholar 

  • Tierney, L. andKadane, J. B. (1986), Accurate approximations for posterior moments and marginal densities,J. Amer. Statist. Assoc., 81, 82–86.

    Article  MATH  MathSciNet  Google Scholar 

  • Tierney, L., Kass, R. E. andKadane, J. B. (1989), Fully Laplace approximation to expectations and variances of nonpositive functions,J. Amer. Statist. Assoc., 84, 710–716.

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University College London, London, UK

    Constantinos Goutis

Authors
  1. Constantinos Goutis
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Goutis, C. Bayesian estimation methods for contingency tables. J. It. Statist. Soc. 2, 35–54 (1993). https://doi.org/10.1007/BF02589074

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02589074

Keywords

Search

Navigation