Non parametric mixture priors based on an exponential random scheme
Tóm tắt
We propose a general procedure for constructing nonparametric priors for Bayesian inference. Under very general assumptions, the proposed prior selects absolutely continuous distribution functions, hence it can be useful with continuous data. We use the notion ofFeller-type approximation, with a random scheme based on the natural exponential family, in order to construct a large class of distribution functions. We show how one can assign a probability to such a class and discuss the main properties of the proposed prior, namedFeller prior. Feller priors are related to mixture models with unknown number of components or, more generally, to mixtures with unknown weight distribution. Two illustrations relative to the estimation of a density and of a mixing distribution are carried out with respect to well known data-set in order to evaluate the performance of our procedure. Computations are performed using a modified version of an MCMC algorithm which is briefly described.
Tài liệu tham khảo
Altomare F, Campiti M (1994)Korovkin-type approximation theory and its application. W. de Gruyter, Berlin
Antoniak CE (1974) Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems.Ann. Statist. 2, 1152–1174
Billingsley P (1968) Convergence of probability measure. Wiley, New York
Cifarelli DM, Muliere P, Secchi P (1999) Prior processes for Bayesian nonparametrics.Technical Report no. 377/P, Dip. Mat. F. Brioschi, Politecnico di Milano
Consonni G, Veronese P (1995) A Bayesian method for combining results from several binomial experiments.J. Amer. Statist. Assoc. 90, 935–944
Dalal SR, Hall WJ (1983) Approximating priors by mixtures of natural conjugate priors.J. Roy. Statist. Soc. Ser. B 45, 278–286
Diaconis P, Ylvisaker D (1985) Quantifying prior opinion. In: Bernardo JM, deGroot MH, Lindley DV, Smith AFM (eds)Bayesian statistics 2, pp 133–156. Elsevier, North Holland
Escobar MD, West M (1995) Bayesian density estimation and inference using mixtures.J. Amer. Statist. Assoc. 90, 577–587
Feller W (1971) An introduction to probability theory and its applications, Vol. II, Wiley, New York
Ferguson TS (1983) Bayesian density estimation by mixtures of normal distributions. In: Rizvi H, Rustagi J (eds) Recent advances in statistics, pp 287–302. Academic Press, New York
George EI (1986) Combining minimax shrinkage estimators.J. Amer. Statist. Assoc. 81, 437–445
Ghosal S, Ghosh JK, Ramamoorthi RV (1999) Posterior consistency of Dirichlet mixtures in density estimation.Ann. Statist. 27, 143–158
Green PJ, Richardson S (1999) Modelling heterogeneity with and without the Dirichlet process.Technical report, University of Bristol. http://www.stats.bris.ac.uk/~peter/
Ishwaran H, Zarepour M (2000) Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models.Biometrika 87, 371–390
Lo AY (1984) On a class of Bayesian nonparametric estimates, density estimates.Ann. Statist. 12, 351–357
Muliere P, Tardella L (1998) Approximating distributions of functionals of Ferguson-Dirichlet priors.Can. J. Statist. 26, 283–297
Petrone S (1999) Random Bernstein polynomials.Scand. J. Statist. 26, 373–393
Petrone S, Veronese P (2001) Feller operators based on natural exponential families.Studi Statistici 60, Istituto Metodi Quantitativi, Università L. Bocconi, Milano
Petrone S, Wasserman L (2002) Consistency of Bernstein posterior.J. Roy. Stat. Soc., Ser. B, 64, 79–100
Prakasa Rao BLS (1983) Nonparametric Functional Estimation. Academic Press, Orlando
Roeder K (1990) Density estimation with confidence sets exemplified by superclusters and voids in the galaxies.J. Amer. Statist. Assoc. 85, 617–624
Sethuraman J (1994) A constructive definition of Dirichlet priors.Statist. Sinica 4, 639–650
Smith B (1999)Bayesian output analysis program (BOA). Department of Biostatistics. School of Public Health, University of Iowa
Tenbusch A (1995)Nonparametric curve estimation with Bernstein estimates. Universitätsverlag Rasch, Osnabrück, Germany