Bayesian Analysis

On the multimodality of random probability measures

George Kokolakis and George Kouvaras

Full-text: Open access

Abstract

Nonparametric methods for density estimation are examined here. Within a Bayesian setting the construction of an absolutely continuous random probability measure is often required for nonparametric statistical analysis. To achieve this we propose a "partial convexification" procedure of a process, such as the Dirichlet, resulting in a multimodal distribution function with a finite expected number of modes. In agreement with convexity theory results, it is shown that the derived random probability measure admits a density with respect to Lebesgue measure.

Article information

Source
Bayesian Anal., Volume 2, Number 1 (2007), 213-219.

Dates
First available in Project Euclid: 22 June 2012

Permanent link to this document
https://projecteuclid.org/euclid.ba/1340390068

Digital Object Identifier
doi:10.1214/07-BA208

Mathematical Reviews number (MathSciNet)
MR2289928

Zentralblatt MATH identifier
1331.62199

Subjects
Primary: Database Expansion Item

Keywords
convexity Dirichlet process multimodal distribution functions Polya trees random probability measures

Citation

Kokolakis, George; Kouvaras, George. On the multimodality of random probability measures. Bayesian Anal. 2 (2007), no. 1, 213--219. doi:10.1214/07-BA208. https://projecteuclid.org/euclid.ba/1340390068


Export citation

References

  • Antoniak, C. (1974). "Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems." Annals of Statistics, 2: 1152–1174.
  • Blackwell, D. and MacQueen, J. (1973). "Ferguson distributions via Polya schemes." Annals of Statistics, 1: 353–355.
  • Brunner, L. (1992). "Bayesian nonparametric methods for data from a unimodal density." Statistics and Probability Letters, 14: 195–199.
  • Escobar, M. and West, M. (1995). "Bayesian density estimation and inference using mixtures." JASA, 90: 577–588.
  • Feller, W. (1971). An Introduction to Probability Theory and its Applications, volume 2. New York: Wiley, 2nd edition.
  • Ferguson, T. S. (1973). "A Bayesian analysis of some nonparametric problems." Annals of Statistics, 1: 209–230.
  • –- (1974). "Prior distributions on spaces of probability measures." Annals of Statistics, 2: 615–629.
  • Hansen, M. and Lauritzen, S. (2002). "Nonparametric Bayes inference for concave distribution functions." Statistica Neerlandica, 56: 110–127.
  • Kokolakis, G. (1983). "A new look at the problem of classification with binary data." Statistician, 32: 144–152.
  • Kokolakis, G. and Dellaportas, P. (1996). "Hierarchical modelling for classifying binary data." In Bayesian Statistics 5, 647–652. London: Oxford University Press.
  • Lavine, M. (1992). "Some aspects of Polya tree distributions for statistical modelling." Annals of Statistics, 20: 1222–1235.
  • –- (1994). "More aspects of Polya tree distributions for statistical modelling." Annals of Statistics, 22: 1161–1176.
  • MacEachern, S. (1994). "Estimating normal means with a conjugate style Dirichlet process prior." Communications in Statistics. Simulation and Computation, 23: 727–741.
  • Sethuraman, J. (1994). "A constructive definition of Dirichlet prior." Statistica Sinica, 4: 639–650.
  • Walker, S., Damien, P., Laud, P., and Smith, A. (1999). "Bayesian nonparametric inference for random distributions and related functions (with discussion)." Journal of the Royal Statistical Society - Series B, 61: 485–528.