Abstract
A two parameter generalized logarithmic series distribution is used to model the number of publications written by biologists. In this paper, some methods of sampling from the generalized logarithmic series distribution are presented. The inversion algorithm is compared with algorithms based on rejection and branching methods. For small values of the parameters, the inversion algorithm seems to be faster than other algorithms. The paper recommends a modified algorithm based on the inversion and branching methods.
Zusammenfassung
Mit einer verallgemeinerten logarithmischen Verteilung läßt sich z.B. die Anzahl der Veröffentlichung von Biologen beschreiben. In dieser Arbeit präsentieren wir Methoden zur Erzeugung von Stichproben aus einer solchen Verteilung: Wir vergleichen Inversion mit Verwerfungsalgorithmen und Verzweigungsmethoden. Es scheint, daß Inversion für kleine Parameterwerte schneller als andere Algorithmen ist. Die Arbeit empfiehlt eine Verbindung von Inversion und Verzweigung.
Similar content being viewed by others
References
Chen, H. C., Asau, Y.: On generating random variates from an empirical distribution. AIIE Trans.6, 163–166 (1974).
Devroye, L.: Non-uniform random variate generation. New York: Springer 1986.
Devroye, L.: Random variate generators for the Poisson-Poisson and related distributions. Comput. Stat. Data Anal.8, 247–278 (1989).
Devroye, L.: The branching process method in Lagrange random variate generation. Comm. Stat. Simul. Comput.21, 1–14 (1992).
Famoye, F.: A short note on the generalized logarithmic series distribution. Stat. Prob. Lett.5, 315–316 (1987).
Jain, G. C., Gupta, R. P.: A logarithmic type distribution. Trab. Estad.24, 99–105 (1973).
Kemp, C. D., Kemp, A. W.: Rapid generation of frequency tables. Appl. Stat.36, 277–282 (1987).
Kemp, C. D., Kemp. A. W.: Poisson random variate generation. Appl. Stat.40, 143–158 (1991).
Kronmal, R. A., Peterson, A. V.: On the alias method for generating random variables from a discrete distribution. Am. Stat.33, 214–218 (1979).
Schmeiser, B. W., Kachitvichyanukul, V.: Poisson random variate generation. Research Memorandum, pp. 81–84. Purdue University School of Industrial Engineering, West Lafayette.
Walker, A. J.: New fast method for generating discrete random numbers with arbitrary frequency distributions. Electr. Lett.10, 127–128 (1974).
Walker, A. J.: An efficient method for generating discrete random variables with general distributions. ACM Trans. Math. Software3, 253–256 (1977).
Whittaker, E. T., Watson, G. N.: A course of modern analysis. Cambridge: Cambridge University Press 1972.
Author information
Authors and Affiliations
Additional information
This article was written while the author was spending his sabbatical leave at the Department of Statistics, University of Kentucky-Lexington.
Rights and permissions
About this article
Cite this article
Famoye, F. Sampling from the generalized logarithmic series distribution. Computing 58, 365–375 (1997). https://doi.org/10.1007/BF02684348
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02684348