A universal generator for discrete log-concave distributions

Wolfgang Hörmann

Publication: Working/Discussion PaperWU Working Paper

Abstract

We give an algorithm that can be used to sample from any discrete log-concave distribution (e.g. the binomial and hypergeometric distributions). It is based on rejection from a discrete dominating distribution that consists of parts of the geometric distribution. The algorithm is uniformly fast for all discrete log-concave distributions and not much slower than algorithms designed for a single distribution. (author's abstract)
Original languageEnglish
Place of PublicationVienna
PublisherInstitut für Statistik und Mathematik, Abt. f. Angewandte Statistik u. Datenverarbeitung, WU Vienna University of Economics and Business
Publication statusPublished - 1993

Publication series

NamePreprint Series / Department of Applied Statistics and Data Processing
No.8

WU Working Paper Series

  • Preprint Series / Department of Applied Statistics and Data Processing

Cite this