Summary
The paper proposes an MCMC algorithm to derive the posterior distribution of the different partially exchangeable structures (models) involved in a Hierarchical Partition Model (HPM). The suggested procedure operates only on the discrete space of the models since it is possible to compute the posterior distribution of the parameters in an exact way for each given model. The performance of the algorithm is discussed in details and it appears satisfactory both when the number of possible models is small or huge. However, in the latter case too many models are typically singled out because the likelihood is essentially constant over them; this suggests the necessity of some form of aa priori model pruning.
Similar content being viewed by others
References
Chib, S. andGreenberg, E. (1994), Understanding Metropolis-Hastings Algorithm.The American Statistician, 49, 327–335.
Consonni, G. andVeronese, P. (1995), A Bayesian method for combining results from several binomial experiments.J. American Statistical Association, 90, 935–944.
Consonni, G. andVeronese, P. (1996), Modelli gerarchici partizionali per l’identificazione ed il trattamento di osservazioni eccezionali. InAtti della XXXVIII Riunione Scientifica della S.I.S., 733–740. Maggioli Editore.
Green, P. J. (1995), Reversible jump Markov chain Monte Carlo computation and Bayesian model determination.Biometrika, 82, 711–732.
Malec, D. andSedransk, J. (1992), Bayesian methodology for combining the results from different experiments when the specifications for pooling are uncertain.Biometrika, 79, 593–601.
Author information
Authors and Affiliations
Additional information
The research by P.V. was partially supported by MURST, Italy.
Rights and permissions
About this article
Cite this article
Sampietro, S., Veronese, P. An MCMC algorithm for bayesian analysis of Hierarchical Partition Models. J. Ital. Statist. Soc. 7, 209–220 (1998). https://doi.org/10.1007/BF03178930
Issue Date:
DOI: https://doi.org/10.1007/BF03178930