Electronic Journal of Statistics

On the topological support of species sampling priors

Pier Giovanni Bissiri and Andrea Ongaro

Full-text: Open access

Abstract

In Bayesian nonparametric statistics, it is crucial that the support of the prior is very large. Here, we consider species sampling priors. Such priors are widely used within mixture models and it has been shown in the literature that a large support for the mixing prior is essential to ensure the consistency of the posterior. In this paper, simple conditions are given that are necessary and sufficient for the support of a species sampling prior to be full. In particular, for proper species sampling priors, the condition is that the maximum size of the atoms of the corresponding process is small with positive probability. We apply this result to show that the main classes of species sampling priors known in literature have full support under mild conditions. Moreover, we find priors with a very simple construction still having full support.

Article information

Source
Electron. J. Statist., Volume 8, Number 1 (2014), 861-882.

Dates
First available in Project Euclid: 26 June 2014

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1403812155

Digital Object Identifier
doi:10.1214/14-EJS912

Mathematical Reviews number (MathSciNet)
MR3229100

Zentralblatt MATH identifier
1348.62102

Subjects
Primary: 62F15: Bayesian inference 62G99: None of the above, but in this section

Keywords
Bayesian nonparametrics consistency of posteriors Dirichlet process species sampling priors topological support of measures

Citation

Bissiri, Pier Giovanni; Ongaro, Andrea. On the topological support of species sampling priors. Electron. J. Statist. 8 (2014), no. 1, 861--882. doi:10.1214/14-EJS912. https://projecteuclid.org/euclid.ejs/1403812155


Export citation

References

  • [1] Bhattacharya, A. and Dunson, D. (2012). Strong consistency of nonparametric Bayes density estimation on compact metric spaces with applications to specific manifolds. Ann. I. Stat. Math. 64 687–714.
  • [2] Billingsley, P. (1968). Convergence of Probability Measures. John Wiley & Sons Inc., New York.
  • [3] Bissiri, P. G., Ongaro, A. and Walker, S. G. (2013). Species sampling models: consistency for the number of species. Biometrika 100 771–777.
  • [4] Datta, S. (1991). On the consistency of posterior mixtures and its applications. Ann. Statist. 19 338–353.
  • [5] De Blasi, P., James, L. F. and Lau, J. W. (2010). Bayesian nonparametric estimation and consistency of mixed multinomial logit choice models. Bernoulli 16 679–704.
  • [6] Dunson, D. B. (2009). Nonparametric Bayes local partition models for random effects. Biometrika 96 249–262.
  • [7] Favaro, S., Prünster, I. and Walker, S. G. (2011). On a class of random probability measures with general predictive structure. Scand. J. Stat. 38 359–376.
  • [8] Ferguson, T. S. (1973). A Bayesian analysis of some nonparametric problems. Ann. Statist. 1 209–230.
  • [9] Fuentes-García, R., Mena, R. H. and Walker, S. G. (2010). A new Bayesian nonparametric mixture model. Commun. Stat. Simulat. 39 669–682.
  • [10] Ghosal, S. (2010). The Dirichlet process, related priors and posterior asymptotics. In Bayesian Nonparametrics ( N. L. Hjort, C. Holmes, P. Müller and S. G. Walker, eds.), 35–79. Cambridge Univ. Press, Cambridge.
  • [11] Ghosal, S., Ghosh, J. K. and Ramamoorthi, R. V. (1999). Posterior consistency of Dirichlet mixtures in density estimation. Ann. Statist. 27 143–158.
  • [12] Gnedin, A. (2010). A species sampling model with finitely many types. Elect. Comm. in Probab. 15 79–88.
  • [13] Gnedin, A. and Pitman, J. (2006). Exchangeable Gibbs partitions and Stirling triangles. J. Math. Sciences 138 5674–5685.
  • [14] Hansen, B. and Pitman, J. (2000). Prediction rules for exchangeable sequences related to species sampling. Statist. Probab. Lett. 46 251–256.
  • [15] Hjort, N. L., Holmes, C., Müller, P. and Walker, S. G., eds. (2010). Bayesian Nonparametrics. Cambridge Series in Statistical and Probabilistic Mathematics 28. Cambridge University Press, Cambridge.
  • [16] Ishwaran, H. and James, L. F. (2001). Gibbs sampling methods for stick–breaking priors. J. Am. Stat. Assoc. 96 161–173.
  • [17] Ishwaran, H. and James, L. F. (2003a). Generalized weighted Chinese restaurant processes for species sampling mixture models. Stat. Sinica 13 1211–1235.
  • [18] Ishwaran, H. and James, L. F. (2003b). Some further developements for stick–breaking priors: finite and infinite clustering and classification. Sankhyā 65 577–592.
  • [19] Jang, G. H., Lee, J. and Lee, S. (2010). Posterior consistency of species sampling priors. Stat. Sinica 20 581–593.
  • [20] Kingman, J. F. C. (1993). Poisson Processes. Oxford Studies in Probability 3. The Clarendon Press Oxford University Press, New York. Oxford Science Publications.
  • [21] Lijoi, A., Mena, R. and Prünster, I. (2005). Bayesian nonparametric analysis for a generalized Dirichlet process prior. Stat. Infer. Stoch. Process. 8 283–309.
  • [22] Lijoi, A., Prünster, I. and Walker, S. G. (2008). Investigating nonparametric priors with Gibbs structure. Statist. Sinica 18 1653–1668.
  • [23] Majumdar, S. (1992). On topological support of Dirichlet prior. Stat. Probabil. Lett. 15 385–388.
  • [24] Navarrete, C., Quintana, F. A. and Mueller, P. (2008). Some issues in nonparametric Bayesian modeling using species sampling models. Stat. model. 8 3–21.
  • [25] Nobile, A. and Fearnside, A. T. (2007). Bayesian finite mixtures with an unknown number of components: the allocation sampler. Stat. Comput. 17 147–162.
  • [26] Ongaro, A. (2005). Size–biased sampling and discrete nonparametric Bayesian inference. J. Statist. Plann. Inference 128 123–148.
  • [27] Ongaro, A. and Cattaneo, C. (2004). Discrete random probability measures: a general framework for nonparametric Bayesian inference. Stat. Probabil. Lett. 67 33–45.
  • [28] Parthasarathy, K. R. (1967). Probability Measures on Metric Spaces. Academic Press, New York.
  • [29] Perman, M., Pitman, J. and Yor, M. (1992). Size-biased sampling of Poisson point processes and excursions. Probab. Theory Rel. 92 21–39.
  • [30] Pitman, J. (1995). Exchangeable and partially exchangeable random partitions. Probab. Theory Rel. 102 145–158.
  • [31] Pitman, J. (1996). Some developments of the Blackwell-MacQueen urn scheme. In Statistics, Probability and Game Theory. IMS Lecture Notes Monogr. Ser. 30 245–267. Inst. Math. Statist., Hayward, CA.
  • [32] Pitman, J. (2003). Poisson-Kingman partitions. Lecture Notes-Monograph Series 40 1–34.
  • [33] Pitman, J. and Yor, M. (1997). The two–parameter Poisson-Dirichlet distribution derived from a stable subordinator. Ann. Probab. 25 855–900.
  • [34] Prünster, I. and Lijoi, A. (2009). Models beyond the Dirichlet process. In Bayesian Nonparametrics: Principles and Practice ( N. Hjort, C. Holmes, P. Müeller and S. Walker, eds.), 80–136. Cambridge University Press, Cambridge, UK.
  • [35] Richardson, S. and Green, P. J. (1997). On Bayesian analysis of mixtures with an unknown number of components. J. R. Statist. Soc. B 59 731–792.
  • [36] Sethuraman, J. (1994). A constructive definition of Dirichlet priors. Statist. Sinica 4 639–650.
  • [37] Stephens, M. (2000). Bayesian analysis of mixture models with an unknown number of components – an alternative to reversible jump methods. Ann. Stat. 28 40–74.
  • [38] Teh, Y. W. and Jordan, M. I. (2010). Hierarchical Bayesian nonparametric models with applications. In Bayesian Nonparametrics ( N. L. Hjort, C. Holmes, P. Müller and S. G. Walker, eds.), 158–207. Cambridge Univ. Press, Cambridge.
  • [39] Wu, Y. and Ghosal, S. (2008). Kullback Leibler property of kernel mixture priors in Bayesian density estimation. Electron. J. Stat. 2 298–331.