English

Computing the distribution of the maximum in balls-and-boxes problems, with application to clusters of disease cases

Statistics Theory 2009-11-11 v1 Combinatorics Statistics Theory

Abstract

We present a rapid method for the exact calculation of the cumulative distribution function of the maximum of multinomially distributed random variables. The method runs in time O(mn)O(mn), where mm is the desired maximum and nn is the number of variables. We apply the method to the analysis of two situations where an apparent clustering of cases of a disease in some locality has raised the possibility that the disease might be communicable, and this possibility has been discussed in the recent literature. We conclude that one of these clusters may be explained on purely random grounds, whereas the other may not.

Cite

@article{arxiv.math/0610810,
  title  = {Computing the distribution of the maximum in balls-and-boxes problems, with application to clusters of disease cases},
  author = {Warren J. Ewens and Herbert S. Wilf},
  journal= {arXiv preprint arXiv:math/0610810},
  year   = {2009}
}