Skip to main content

A Bayesian approach for the estimation of probability distributions under finite sample space

Abstract

In this article, we describe a Bayesian approach for the estimation of probability distribution of a discrete random variable (rv) with correlated classes under finite sample space. We utilize general benefits of Bayesian approaches within the context of estimation of probability distributions under finite sample space. In our approach, a tractable posterior distribution is obtained; and hence, posterior inferences are easily drawn by using the Gibbs sampling. Possible prior correlations between adjacent categories of the considered discrete rv are suitably modeled. The proposed approach takes into account all available information contained in successive samples as a natural consequence of using Bayes’s theorem. It is beneficial in the estimation of probability distributions for compositional data sets observed in longitudinal studies. We analyze two bar charts from two health surveys in Italy for illustrative purposes and apply our approach to a data set from general elections of Turkey.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  • Argiento R, Guglielmi A, Pievatolo A (2014) Estimation, prediction and interpretation of NGG random effects models: an application to Kevlar fibre failure times. Stat Pap 55:805–826

    MathSciNet  Article  MATH  Google Scholar 

  • Box G, Tiao C (1973) Bayesian inference in statistical analysis. Addison-Wesley, London

    MATH  Google Scholar 

  • Branscum A, Hanson T, Gardner I (2008) Bayesian non-parametric models for regional prevalence estimation. J Appl Stat 35:567–582

    MathSciNet  Article  MATH  Google Scholar 

  • Christensen R, Johnson W, Branscum A, Hanson T (2010) Bayesian ideas and data analysis: an introduction for scientists and statisticians. Chapman and Hall/CRC, New York

    MATH  Google Scholar 

  • Conti S, Farchi G, Minelli G, Buiatti E, Balzi D, Arniani S, Naldoni P, Gargiulo L, Gianicolo E, Sabbadini L (2007) Health observation compared to health reporting findings from a pilot study in florence. Ann Epidemiol 17:999–1003

    Article  Google Scholar 

  • Demirhan H (2013) Bayesian estimation of order-restricted and unrestricted association models. J Multivar Anal 121:109–126

    MathSciNet  Article  MATH  Google Scholar 

  • Demirhan H, Hamurkaroglu C (2006) A Bayesian approach to the estimation of expected cell counts by using log linear models. Commun Stat—Theor M 35:325–335

    MathSciNet  MATH  Google Scholar 

  • Demirhan H, Hamurkaroglu C (2008) Bayesian estimation of log odds ratios from \({R} \times {C}\) and \(2 \times 2 \times {K}\) contingency tables. Stat Neerl 62:405–512

    MathSciNet  Article  Google Scholar 

  • Dickey J, Jiang T (1998) Filtered-variate prior distributions for histogram smoothing. J Am Stat Assoc 93:651–662

    MathSciNet  Article  MATH  Google Scholar 

  • Gelman A (1996) Inference and monitoring convergence. Markov chain Monte Carlo in practice. Chapman and Hall/CRC, London

    Google Scholar 

  • Hanson T, Jara A (2013) Surviving fully Bayesian nonparametric regression models. Bayesian theory and applications. Oxford University Press, Oxford, pp 592–615

    Google Scholar 

  • Hupkens C, van den Berg J, van der Zee J (1999) National health interview surveys in europe: an overview. Health Policy 47:145–168

    Article  Google Scholar 

  • Kaynar M (2007) Political parties of Republic period of 1923–2006 (Cumhuriyet Donemi Siyasi Partileri 1923–2006). Imge, Ankara

    Google Scholar 

  • King R, Brooks S (2001) Prior induction in log-linear models for general contingency table analysis. Ann Stat 29:715–747

    MathSciNet  Article  MATH  Google Scholar 

  • Leonard T (1973) Bayesian method for histograms. Biometrika 60:297–308

    MathSciNet  MATH  Google Scholar 

  • Leonard T (1978) Density estimation, stochastic processes and prior information. J Roy Stat Soc 40:113–146

    MathSciNet  MATH  Google Scholar 

  • Mostofi A, Kharrati-Kopaei M (2012) Bayesian nonparametric inference for unimodal skew-symmetric distributions. Stat Pap 53:821–832

    MathSciNet  Article  MATH  Google Scholar 

  • Petrone S (1999) Bayesian density estimation using Bernstein polynomials. Can J Stat 27:105–126

    MathSciNet  Article  MATH  Google Scholar 

  • Rodrigues P, Lima A (2009) Analysis of an european union election using principal component analysis. Stat Pap 50:895–904

    MathSciNet  Article  MATH  Google Scholar 

  • Thorburn D (1986) A Bayesian approach to density estimation. Biometrika 73:65–75

    MathSciNet  Article  MATH  Google Scholar 

  • Titterington D (1985) Common structure of smoothing techniques in statistics. Int Stat Rev 53:141–170

    MathSciNet  Article  MATH  Google Scholar 

Download references

Acknowledgments

We would like to thank two anonymous reviewers and editor for constructive criticisms and valuable comments that improved the clarity of the article.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Haydar Demirhan.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Demirhan, H., Demirhan, K. A Bayesian approach for the estimation of probability distributions under finite sample space. Stat Papers 57, 589–603 (2016). https://doi.org/10.1007/s00362-015-0669-z

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00362-015-0669-z

Keywords

  • Bar chart
  • Compositional data
  • Dirichlet process prior
  • Elections
  • Polya trees
  • Truncated log normal distribution