Electronic Journal of Statistics

Exchangeable Bernoulli random variables and Bayes’ postulate

Moulinath Banerjee and Thomas Richardson

Full-text: Open access


We discuss the implications of Bayes’ postulate in the setting of exchangeable Bernoulli random variables. Bayes’ postulate, here, stipulates a uniform distribution on the total number of successes in any number of trials. For an infinite sequence of exchangeable Bernoulli variables the conditions of Bayes’ postulate are equivalent to a uniform (prior) distribution on the underlying mixing variable which necessarily exists by De Finetti’s representation theorem. We show that in the presence of exchangeability, the conditions of Bayes’ postulate are implied by a considerably weaker assumption which only specifies the probability of $n$ successes in $n$ trials, for every $n$. The equivalence of the Bayes’ postulate and the weak assumption holds for both finite and infinite sequences. We also explore characterizations of the joint distribution of finitely many exchangeable Bernoulli variables in terms of probability statements similar to the weak assumption. Finally, we consider extensions of Bayes’ postulate in the framework of exchangeable multinomial trials.

Article information

Electron. J. Statist., Volume 7 (2013), 2193-2208.

First available in Project Euclid: 16 September 2013

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62A01: Foundations and philosophical topics
Secondary: 62C10: Bayesian problems; characterization of Bayes procedures

Bernoulli random variables Bayes’ postulate exchangeability multinomial trials weak assumption


Banerjee, Moulinath; Richardson, Thomas. Exchangeable Bernoulli random variables and Bayes’ postulate. Electron. J. Statist. 7 (2013), 2193--2208. doi:10.1214/13-EJS835. https://projecteuclid.org/euclid.ejs/1379336968

Export citation


  • Aldous, D. (1985). Exchangeability and related topics. In Hennequin, P., editor, École d’Été de Probabilités de Saint–Flour XIII 1983, pages 1–198. Springer-Verlag, Heidelberg. Lecture Notes in Mathematics 1117.
  • Bayes, T. (1763). An Essay towards solving a problem in the doctrine of chances., Philosophical Transactions of the Royal Society of London, 53, 370–418.
  • Coolen, F.P.A. (1998A). Bayes’ postulate repostulated. Contributed to, 6th Valencia International Meeting on Bayesian Statistics, Alcossebre, Spain (May/June 1998). Available at http://citeseerx.ist.psu.edu/viewdoc/summary?doi=
  • Coolen, F.P.A. (1998B). Low structure imprecise predictive inference for Bayes’ problem., Statistics and Probability Letters, 36, 349–357.
  • de Finetti, B. (1930). Funzione caratteristica di un fenomeno aleatorio., Atti Reale Accademia Nazionale de Lincei, Mem., 4, 86–133.
  • de Finetti, B. (1964). Foresight: Its Logical Laws, its subjective sources, (English translation of, La prévision: ses lois logiques, ses sources subjectives. Annales de l’Institut Henri Poincaré. 1937; VII: 1–68. trans. H.E. Kyburg) in Studies in Subjective Probability, H.E. Kyburg & H.E. Smokler (eds), Wiley, New York.
  • Diaconis, P. (1977). Finite forms of De Finetti’s theorem on exchangeability., Synthese 36, 271–181.
  • Diaconis, P. and Freedman, D. (1980). Finite exchangeable sequences., Annals of Probability 8, 745–764.
  • Diniz, M.A. and Polpo, A. (2012). Bayes’ postulate for trinomial trials., AIP Conference Proceedings, 1490, 108–115.
  • Diniz, M.A. and Polpo, A. (2013). A simple proof for the multinomial version of the Representation Theorem. Available at, http://www.mi.imati.cnr.it/conferences/BAYSM2013/papers/baysm10.pdf.
  • Drton, M. and Richardson, T.S. (2008). Binary models for marginal independence., Journal of the Royal Statistical Society Series B, 70, 287–309.
  • Edwards, A.W.F. (1978). Commentary on the arguments of Thomas Bayes., Scandinavian Journal of Statistics, 5, 116–118.
  • Good, I.J. (1979). Bayes’ Billiard-Table Argument Extended to Multinomials., Journal of Statistical Computation and Simulation, 9(2), 161–163.
  • Hewitt, E. and Savage, L.J. (1955). Symmetric measures on Cartesian products., Transactions of the American Mathematical Society, 80, 470–501.
  • Hill, B.M. (1968). Posterior distribution of percentile Bayes’ theorem for sampling from a population., Journal of the American Statistical Association, 63, 677–691.
  • Hill, B.M. (1993). Parametric models for $A_(n)$: Splitting processes and mixtures., Journal of the Royal Statistical Society Series B, 55(2), 423–433.
  • Molina, E.C. (1931). Bayes’ Theorem: An expository presentation., Annals of Mathematical Statistics, 2, 23–37.
  • Murray, F.H. (1930). Note on a scholium of Bayes., Bulletin of the American Mathematical Society, 36, 129–132.
  • Schrieber, F. (1987). The Extended Bayes-Postulate, Its Potential Effect on Statistical Methods and Some Historical Aspects., Probability and Bayesian Statistics, pages 423–430. Springer, US.
  • Stigler, S.M. (1986)., The History of Statistics. The Belknap Press of Harvard University Press. Cambridge, MA & London, England.
  • Stigler, S.M. (1982). Thomas Bayes’s Bayesian inference., Journal of the Royal Statistical Society Series A, 145(2), 250–258.
  • Wood, G.R. (1992). Binomial mixtures and finite exchangeability., Annals of Probability, 20, 1167–1173