Hostname: page-component-89b8bd64d-sd5qd Total loading time: 0 Render date: 2026-05-12T17:36:04.389Z Has data issue: false hasContentIssue false
  • English
  • Français

A Pólya Approximation to the Poisson-Binomial Law

Part of: Limit theorems Distribution theory Combinatorial probability

Published online by Cambridge University Press:  04 February 2016

Max Skipper
Max Skipper*
Affiliation:
University of Oxford and The University of Sydney
*
∗ Postal address: School of Mathematics and Statistics, The University of Sydney, Sydney, 2006, Australia. Email address: m.skipper@maths.usyd.edu.au
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

Using Stein's method, we derive explicit upper bounds on the total variation distance between a Poisson-binomial law (the distribution of a sum of independent but not necessarily identically distributed Bernoulli random variables) and a Pólya distribution with the same support, mean, and variance; a nonuniform bound on the pointwise distance between the probability mass functions is also given. A numerical comparison of alternative distributional approximations on a somewhat representative collection of case studies is also exhibited. The evidence proves that no single one is uniformly most accurate, though it suggests that the Pólya approximation might be preferred in several parameter domains encountered in practice.

Keywords

Stein's methodPoisson-binomial approximationBernoulli variable

MSC classification

Primary: 62E17: Approximations to distributions (nonasymptotic)
Secondary: 60F05: Central limit and other weak theorems 60C99: None of the above, but in this section

Information

Type
Research Article
Information
Journal of Applied Probability , Volume 49 , Issue 3 , September 2012 , pp. 745 - 757
Copyright
© Applied Probability Trust 

References

Barbour, A. D. (2005). Multivariate Poisson-binomial approximation using Stein's method. In Stein's Method and Applications (Lecture Notes Ser. Inst. Math. Sci. Natl. Univ. Singapore 5), Singapore University Press, pp. 131–142.Google Scholar
Barbour, A. D. and Chen, L. H. Y. (eds) (2005). An Introduction to Stein's Method (Lecture Notes Ser. Inst. Math. Sci. Natl. Univ. Singapore 4). Singapore University Press.Google Scholar
Barbour, A. D. and Jensen, J. L. (1989). Local and tail approximations near the Poisson limit. Scand. J. Statist. 16, 75–87.Google Scholar
Barbour, A. D. and Xia, A. (2006). On Stein's factors for Poisson approximation in Wasserstein distance. Bernoulli 12, 943–954.Google Scholar
Barbour, A. D., Chen, L. H. Y. and Loh, W.-L. (1992). Compound Poisson approximation for nonnegative random variables via Stein's method. Ann. Prob. 20, 1843–1866.CrossRefGoogle Scholar
Barbour, A. D., Holst, L. and Janson, S. (1992). Poisson Approximation (Oxford Stud. Prob. 2). Clarendon Press, Oxford University Press, New York.Google Scholar
Borovkov, K. and Pfeifer, D. (1996). On improvements of the order of approximation in the Poisson limit theorem. J. Appl. Prob. 33, 146–155.CrossRefGoogle Scholar
Brown, T. C. and Xia, A. (2001). Stein's method and birth–death processes. Ann. Prob. 29, 1373–1403.Google Scholar
Čekanavičius, V. (1997). Asymptotic expansions in the exponent: a compound Poisson approach. Adv. Appl. Prob. 29, 374–387.Google Scholar
Čekanavičius, V. and Roos, B. (2004). Two-parametric compound binomial approximations. Liet. Mat. Rink. 44, 443–466. English translation: Lithuanian Math. J. 44, 354-373.Google Scholar
Čekanavičius, V. and Roos, B. (2006). Compound binomial approximations. Ann. Inst. Statist. Math. 58, 187–210.CrossRefGoogle Scholar
Čekanavičius, V. and Roos, B. (2006). An expansion in the exponent for compound binomial approximations. Liet. Mat. Rink. 46, 67–110. English translation: Lithuanian Math. J. 46, 54-91.Google Scholar
Čekanavičius, V. and Va{ı˘tkus, P.} (2001). Centered Poisson approximation by the Stein method. Liet. Mat. Rink. 41, 409–423 (in Russian). English translation: Lithuanian Math. J. 41, 319-329.Google Scholar
Chatterjee, S., Diaconis, P. and Meckes, E. (2005). Exchangeable pairs and Poisson approximation. Prob. Surveys 2, 64–106.Google Scholar
Chen, S. X. and Liu, J. S. (1997). Statistical applications of the Poisson-binomial and conditional Bernoulli distributions. Statist. Sinica 7, 875–892.Google Scholar
Choi, K. P. and Xia, A. (2002). Approximating the number of successes in independent trials: binomial versus Poisson. Ann. Appl. Prob. 12, 1139–1148.Google Scholar
Ehm, W. (1991). Binomial approximation to the Poisson binomial distribution. Statist. Prob. Lett. 11, 7–16.Google Scholar
Eichelsbacher, P. and Reinert, G. (2008). Stein's method for discrete Gibbs measures. Ann. Appl. Prob. 18, 1588–1618.Google Scholar
Hoggar, S. G. (1974). Chromatic polynomials and logarithmic concavity. J. Combinatorial Theory B 16, 248–254.Google Scholar
Johnson, N. L., Kotz, S. and Kemp, A. W. (1992). Univariate Discrete Distributions, 2nd edn. John Wiley, New York.Google Scholar
Jurgelenaite, R., Lucas, P. and Heskes, T. (2005). Exploring the noisy threshold function in designing Bayesian networks. In Research and Development in Intelligent Systems XXII (Proc. SGAI Internat. Conf. Innovative Techniques and Applications of Artificial Intelligence), eds Bramer, M., Coenen, F. and Allen, T., Springer, London, pp. 133–146.Google Scholar
Kruopis, Y. (1986). The accuracy of approximation of the generalized binomial distribution by convolutions of Poisson measures. Litovsk. Mat. Sb. 26, 53–69.Google Scholar
Mattner, L. and Roos, B. (2007). A shorter proof of Kanter's Bessel function concentration bound. Prob. Theory Relat. Fields 139, 191–205.Google Scholar
Peköz, E. A., Röllin, A., Čekanavičius, V. and Shwartz, M. (2009). A three-parameter binomial approximation. J. Appl. Prob. 46, 1073–1085.Google Scholar
Percus, O. E. and Percus, J. K. (1985). Probability bounds on the sum of independent nonidentically distributed binomial random variables. SIAM J. Appl. Math. 45, 621–640.Google Scholar
Pitman, J. (1997). Probabilistic bounds on the coefficients of polynomials with only real zeros. J. Combinatorial Theory A 77, 279–303.Google Scholar
Röllin, A. (2008). Symmetric and centered binomial approximation of sums of locally dependent random variables. Electron. J. Prob. 13, 756–776.Google Scholar
Roos, B. (2000). Binomial approximation to the Poisson binomial distribution: the Krawtchouk expansion. Teor. Veroyat. Primen. 45, 328–344. English translation: Theory Prob. Appl. 45 (2001), 258-272.Google Scholar
Skipper, M. M. (2010). Some approximation theorems in discrete probability. , University of Oxford.Google Scholar
Soon, S. Y. T. (1996). Binomial approximation for dependent indicators. Statist. Sinica 6, 703–714.Google Scholar
Stein, C. (1986). Approximate Computation of Expectations (Inst. Math. Statist. Lecture Notes—Monogr. Ser. 7). Institute of Mathematical Statistics, Hayward, CA.Google Scholar
Stein, C. (1990). Application of Newton's identities to a generalized birthday problem and to the Poisson binomial distribution. Tech. Rep. 354, Department of Statistics, Stanford University.Google Scholar
Thompson, P. (2002). Almost-binomial random variables. College Math. J. 33, 235–237.Google Scholar
Vatutin, V. A. and Mikhailov, V. G. (1983). Limit theorems for the number of empty cells in an equiprobable scheme for group allocation of particles. Theory Prob. Appl. 27, 734–743.Google Scholar
Xia, A. and Zhang, F. (2008). A polynomial birth-death point process approximation to the Bernoulli process. Stoch. Process. Appl. 118, 1254–1263.Google Scholar
Xia, A. and Zhang, F. (2009). Polynomial birth-death distribution approximation in the Wasserstein distance. J. Theoret. Prob. 22, 294–310.Google Scholar