Bernoulli

  • Bernoulli
  • Volume 18, Number 4 (2012), 1267-1283.

Asymptotics for a Bayesian nonparametric estimator of species variety

Stefano Favaro, Antonio Lijoi, and Igor Prünster

Full-text: Open access

Abstract

In Bayesian nonparametric inference, random discrete probability measures are commonly used as priors within hierarchical mixture models for density estimation and for inference on the clustering of the data. Recently, it has been shown that they can also be exploited in species sampling problems: indeed they are natural tools for modeling the random proportions of species within a population thus allowing for inference on various quantities of statistical interest. For applications that involve large samples, the exact evaluation of the corresponding estimators becomes impracticable and, therefore, asymptotic approximations are sought. In the present paper, we study the limiting behaviour of the number of new species to be observed from further sampling, conditional on observed data, assuming the observations are exchangeable and directed by a normalized generalized gamma process prior. Such an asymptotic study highlights a connection between the normalized generalized gamma process and the two-parameter Poisson–Dirichlet process that was previously known only in the unconditional case.

Article information

Source
Bernoulli, Volume 18, Number 4 (2012), 1267-1283.

Dates
First available in Project Euclid: 12 November 2012

Permanent link to this document
https://projecteuclid.org/euclid.bj/1352727810

Digital Object Identifier
doi:10.3150/11-BEJ371

Mathematical Reviews number (MathSciNet)
MR2995795

Zentralblatt MATH identifier
1329.62163

Keywords
asymptotics Bayesian nonparametrics completely random measures normalized generalized gamma process polynomially and exponentially tilted random variables $\sigma$-diversity species sampling models two parameter Poisson–Dirichlet process

Citation

Favaro, Stefano; Lijoi, Antonio; Prünster, Igor. Asymptotics for a Bayesian nonparametric estimator of species variety. Bernoulli 18 (2012), no. 4, 1267--1283. doi:10.3150/11-BEJ371. https://projecteuclid.org/euclid.bj/1352727810


Export citation

References

  • [1] Argiento, R., Guglielmi, A. and Pievatolo, A. (2009). A comparison of nonparametric priors in hierarchical mixture modelling for AFT regression. J. Statist. Plann. Inference 139 3989–4005.
  • [2] Argiento, R., Guglielmi, A. and Pievatolo, A. (2010). Bayesian density estimation and model selection using nonparametric hierarchical mixtures. Comput. Statist. Data Anal. 54 816–832.
  • [3] Brix, A. (1999). Generalized gamma measures and shot-noise Cox processes. Adv. in Appl. Probab. 31 929–953.
  • [4] Bunge, J. and Fitzpatrick, M. (1993). Estimating the number of species: A review. J. Am. Statist. Assoc. 88 364–373.
  • [5] Carlton, M.A. (2002). A family of densities derived from the three-parameter Dirichlet process. J. Appl. Probab. 39 764–774.
  • [6] Chao, A. (2005). Species estimation and applications. In Encyclopedia of Statistical Sciences (N. Balakrishnan, C.B. Read and B. Vidakovic, eds.) 12 7907–7916. New York: Wiley.
  • [7] Charalambides, C.A. (2005). Combinatorial Methods in Discrete Distributions. Hoboken, NJ: Wiley.
  • [8] De Blasi, P., Peccati, G. and Prünster, I. (2009). Asymptotics for posterior hazards. Ann. Statist. 37 1906–1945.
  • [9] Devroye, L. (2009). Random variate generation for exponentially and polynomially tilted stable distributions. ACM Trans. Model. Comp. Simul. 19 4.
  • [10] Favaro, S., Lijoi, A., Mena, R.H. and Prünster, I. (2009). Bayesian non-parametric inference for species variety with a two-parameter Poisson–Dirichlet process prior. J. R. Stat. Soc. Ser. B Stat. Methodol. 71 993–1008.
  • [11] Ghosal, S. (2010). The Dirichlet process, related priors and posterior asymptotics. In Bayesian Nonparametrics (N.L. Hjort, C.C. Holmes, P. Müller and S.G. Walker, eds.) 35–79. Cambridge: Cambridge Univ. Press.
  • [12] Gnedin, A. (2010). A species sampling model with finitely many types. Electron. Commun. Probab. 15 79–88.
  • [13] Gnedin, A. and Pitman, J. (2005). Exchangeable Gibbs partitions and Stirling triangles. Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklov. (POMI) 325 83–102.
  • [14] Griffin, J., Kolossiatis, M. and Steel, M. F. J. (2010). Modelling overdispersion with the normalized tempered stable distribution. Working Paper 10-01, CRiSM.
  • [15] Griffin, J., Kolossiatis, M. and Steel, M. F. J. (2010). Comparing distributions using dependent normalized random measure mixtures. Working Paper 10-24, CRiSM.
  • [16] Griffin, J.E. and Walker, S.G. (2011). Posterior simulation of normalized random measure mixtures. J. Comput. Graph. Statist. 20 241–259.
  • [17] Griffiths, R.C. and Spanò, D. (2007). Record indices and age-ordered frequencies in exchangeable Gibbs partitions. Electron. J. Probab. 12 1101–1130.
  • [18] Hjort, N.L., Holmes, C.C., Müller P. and Walker S.G. (2010). Bayesian Nonparametrics. Cambridge: Cambridge Univ. Press.
  • [19] James, L.F., Lijoi, A. and Prünster, I. (2006). Conjugacy as a distinctive feature of the Dirichlet process. Scand. J. Statist. 33 105–120.
  • [20] James, L.F., Lijoi, A. and Prünster, I. (2009). Posterior analysis for normalized random measures with independent increments. Scand. J. Stat. 36 76–97.
  • [21] Kingman, J.F.C. (1993). Poisson Processes. Oxford Studies in Probability 3. New York: Oxford Univ. Press.
  • [22] Lijoi, A., Mena, R.H. and Prünster, I. (2005). Hierarchical mixture modeling with normalized inverse-Gaussian priors. J. Amer. Statist. Assoc. 100 1278–1291.
  • [23] Lijoi, A., Mena, R.H. and Prünster, I. (2007). Bayesian nonparametric estimation of the probability of discovering new species. Biometrika 94 769–786.
  • [24] Lijoi, A., Mena, R.H. and Prünster, I. (2007). Controlling the reinforcement in Bayesian non-parametric mixture models. J. R. Stat. Soc. Ser. B Stat. Methodol. 69 715–740.
  • [25] Lijoi, A. and Prünster, I. (2010). Models beyond the Dirichlet process. In Bayesian Nonparametrics (N.L. Hjort, C.C. Holmes, P. Müller and S.G. Walker, eds.) 80–136. Cambridge: Cambridge Univ. Press.
  • [26] Lijoi, A., Prünster, I. and Walker, S.G. (2008). Bayesian nonparametric estimators derived from conditional Gibbs structures. Ann. Appl. Probab. 18 1519–1547.
  • [27] Lijoi, A., Prünster, I. and Walker, S.G. (2008). Investigating nonparametric priors with Gibbs structure. Statist. Sinica 18 1653–1668.
  • [28] Montagna, S. (2009). Random probability measures and their applications to Bayesian Nonparametrics. M.Sc. thesis, Collegio Carlo Alberto, Moncalieri, Italy.
  • [29] Navarrete, C. and Quintana, F.A. (2011). Similarity analysis in Bayesian random partition models. Comput. Statist. Data Anal. 55 97–109.
  • [30] Navarrete, C., Quintana, F.A. and Müller, P. (2008). Some issues in nonparametric Bayesian modelling using species sampling models. Stat. Model. 8 3–21.
  • [31] Peccati, G. and Prünster, I. (2008). Linear and quadratic functionals of random hazard rates: An asymptotic analysis. Ann. Appl. Probab. 18 1910–1943.
  • [32] Pitman, J. (1996). Some developments of the Blackwell–MacQueen urn scheme. In Statistics, Probability and Game Theory (T.S. Ferguson, L.S. Shapley and J.B. MacQueen, eds.). Institute of Mathematical Statistics Lecture Notes—Monograph Series 30 245–267. Hayward, CA: IMS.
  • [33] Pitman, J. (2003). Poisson–Kingman partitions. In Statistics and Science: A Festschrift for Terry Speed (D.R. Goldstein, ed.). Institute of Mathematical Statistics Lecture Notes—Monograph Series 40 1–34. Beachwood, OH: IMS.
  • [34] Pitman, J. (2006). Combinatorial Stochastic Processes. Lecture Notes in Math. 1875. Berlin: Springer.
  • [35] Regazzini, E., Lijoi, A. and Prünster, I. (2003). Distributional results for means of normalized random measures with independent increments. Ann. Statist. 31 560–585.