[go: up one dir, main page]

Skip to main content
Log in

Sampling from the poisson distribution on a computer

Erzeugung Poissonverteilter Zufallszahlen mit einem Computer

  • Published:
Computing Aims and scope Submit manuscript

Abstract

This paper describes a method of sampling from the Poisson distribution on a computer that appears to be less costly than a recently suggested method in [1]. The proposed method relies on a conventional search using the inverse transform approach for nonintegral μ<7, on a modification of the inverse transform approach that begins the search at the mode for integral μ, and on a combination of these two approaches for nonintegral μ>7. For large μ the sampling cost is proportional to μ1/2. The paper also shows that for μ≥15 an incidental error occurs by using max (0, [μ+Yμ1/2+0.5]) whereY is fromN(0,1). Since the sampling cost ofY is a constant, this approach places an upper bound on the cost of generating a Poisson variate.

Zusammenfassung

Diese Arbeit beschreibt eine Methode zur Erzeugung von Poissonverteilten Zufallszahlen mit einem Computer, die schneller zu sein scheint als eine in [1] angegebene Methode. Die empfohlene Methode beruht für nichtganzzahlige μ<7 auf einem konventionellen Suchalgorithmus nach Verwendung der Umkehrtransformation, für ganzzahlige μ auf einer Modifikation davon, wobei die Suche beim Modus beginnt und auf einer Kombination dieser beiden Methoden für nichtganzzahlige μ>7. Für große μ ist die Rechenzeit proportional zu\(\sqrt \mu \). In der Arbeit wird auch gezeigt, daß für μ≥15 bei Verwendung von max (0, [μ +\(Y\sqrt \mu \) + 0.5]), wobeiY nachN(0, 1) verteilt ist, derselbe Fehler auftritt. Da die Rechenzeit fürY eine Konstante ist, liefert diese Methode eine obere Schranke für die Rechenzeit zur Erzeugung nach Poisson verteilter Zufallszahlen.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Ahrens, J. H., Dieter, U.: Computer Methods for Sampling from Gamma, Beta, Poisson and Binomial Distributions. Computing12, 223–246 (1974).

    Google Scholar 

  2. Ahrens, J. H., Dieter, U.: Non-Uniform Random-Numbers. Institut für Math. Statistik, Technische Hochschule in Graz, Austria, 1974.

    Google Scholar 

  3. Molina, E. C.: Poisson's Exponential Binomial Limit. New York: Van Nostrand 1947.

    Google Scholar 

  4. U. S. Department of Commerce, National, Bureau of Standards: Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. Washington, D. C.: U.S. Government Printing Office 1964.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Additional information

I am grateful to Ms. Karen Pitts for programming assistance.

This research was supported by the Office of Naval Research under contract N00014-67-A-0321-0008. Reproduction in whole or in part is permitted for any purpose of the United States government.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Fishman, G.S. Sampling from the poisson distribution on a computer. Computing 17, 147–156 (1976). https://doi.org/10.1007/BF02276759

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02276759

Keywords

Navigation