Analytical proofs for the properties of the probability mass function of the Poisson distribution of order $k$

TL;DR

This paper provides analytical proofs for the properties of the probability mass function of the Poisson distribution of order k, including monotonicity and bounds, with some results based on unproven but supported assumptions.

Contribution

It offers the first analytical proofs of pmf properties for the Poisson distribution of order k, including monotonicity and bounds, advancing theoretical understanding.

Findings

PMF decreases monotonically for small λ when n ≥ k

Difference between mean and mode does not exceed k (conditional proof)

New inequalities and sharper bounds for the distribution

Abstract

The Poisson distribution of order $k$ is a special case of a compound Poisson distribution. For $k=1$ it is the standard Poisson distribution. Our main result is a proof that for sufficiently small values of the rate parameter $\lambda$, the probability mass function (pmf) decreases monotonically for all $n\ge k$ (it is known that the pmf increases strictly for $1\le n \le k$, for fixed $k\ge2$ and all $\lambda>0$). The second main result is a partial proof that the difference (mean $-$ mode) does not exceed $k$. The term `partial proof' signifies that the derivation is conditional on an assumption which, although plausible and supported by numerical evidence, is as yet not proved. This note also presents new inequalities, and sharper bounds for some published inequalities, for the Poisson distribution of order $k$.