Mixed Poisson families with real-valued mixing distributions

2024/07/24 by Townes, F. William · 1 citation
#60E05 (Primary) 62E10 (Secondary) #FOS: Mathematics #G.3 #Probability (math.PR)

paper · doi:10.48550/arxiv.2407.17614

Abstract

Mixed Poisson distributions provide a flexible approach to the analysis of count data with overdispersion, zero inflation, or heavy tails. Since the Poisson mean must be nonnegative, the mixing distribution is typically assumed to have nonnegative support. We show this assumption is unnecessary and real-valued mixing distributions are also possible. Informally, the mixing distribution merely needs to have a light (subexponential) left tail and a small amount of probability mass on negative values. We provide several concrete examples, including the mixed Poisson-extreme stable family, where the mixing distribution has a power law tail.

Cited by

• Broadly discrete stable distributions

Related

• Asymptotic tail properties of Poisson mixture distributions
• A note on mixed Poisson distributions
• Choice of mixture Poisson models based on Extreme value theory
• Broadly discrete stable distributions
• Poisson-modification of the Quasi Lindley distribution and its zero\n modification for over-dispersed count data