Specification of Hyper-Parameters for Normal Prior Distributions Induced on Log-Linear Parameters

Abstract

-

Keywords

• -

References

1. Chen, Z. and Dunson, D. B. Random effects selection in linear mixed models, Biometrics 59, 762–769, 2003.
2. Dellaportas, P. and Forster, J. J. Markov chain Monte Carlo model determination for hier- archical and graphical log-linear models, Biometrika 86, 615–633, 1999.
3. Demirhan, H. Bayesian Estimation of The Parameters and Expected Cell Counts in Loga- rithmic Linear Models (Unpublished M.Sc. thesis, Hacettepe University, Institute of Natural Sciences, Ankara, 2004).
4. Gelman, A. Prior distributions for variance parameters in hierarchical models, www. stat. columbia.edu/ gelman/ research/ unpublished/tau5.pdf, Visit date: February 2004.
5. Geweke, J. Evaluating the accuracy of sampling-based approaches to the calculation of pos- terior moments (with discussion), Bayesian Statistics 4, 169–193, Oxford University Press, Oxford, 1992.
6. King, R. and Brooks, S. P. Prior induction in log-linear models for general contingency table analysis, The Annals of Statistics 29 (3), 715–747, 2001.
7. King, R. and Brooks, S. P. On the analysis of population size, Biometrika 88 (2), 317–336, 2001.
8. Knuiman, M. W. and Speed, T. P. Incorporating prior information into the analysis of con- tingency tables, Biometrics 44, 1061–1071, 1988.

9. Leighty, R. M. and Johnson, W.J. A Bayesian log-linear model analysis of categorical data, Journal of Official Statistics 6 (2), 133–155, 1990.
10. Lenonard, T. Bayesian estimation methods for two-way contingency tables, Journal of Royal Statistical Society, Ser. B 37, 23–37, 1975.
11. Nazaret, W. Bayesian log-linear estimates for three-way contingency tables, Biometrika 74, 401–410, 1987.