An asymptotic expansion for the normalizing constant of the Conway–Maxwell–Poisson distribution

Robert E. Gaunt, Satish Iyengar, Adri Olde Daalhuis, Burcin Simsek

Research output: Contribution to journalArticlepeer-review

Abstract

The Conway–Maxwell–Poisson distribution is a two-parameter generalization of the Poisson distribution that can be used to model data that are under- or over-dispersed relative to the Poisson distribution. The normalizing constant Z (λ, ν) is given by an infinite series that in general has no closed form, although several papers have derived approximations for this sum. In this work, we start by using probabilistic argument to obtain the leading term in the asymptotic expansion of Z(λ, ν) in the limit λ → ∞ that holds for all ν > 0. We then use an integral representation to obtain the entire asymptotic series and give explicit formulas for the first eight coefficients. We apply this asymptotic series to obtain approximations for the mean, variance, cumulants, skewness, excess kurtosis and raw moments of CMP random variables. Numerical results confirm that these correction terms yield more accurate estimates than those obtained using just the leading-order term.
Original languageEnglish
Pages (from-to)163-180
Number of pages18
JournalAnnals of the Institute of Statistical Mathematics
Volume71
Issue number1
Early online date15 Nov 2017
DOIs
Publication statusPublished - Feb 2019

Fingerprint

Dive into the research topics of 'An asymptotic expansion for the normalizing constant of the Conway–Maxwell–Poisson distribution'. Together they form a unique fingerprint.

Cite this