Online Program Home
My Program

Abstract Details

Activity Number: 75 - Probability and Statistics
Type: Contributed
Date/Time: Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
Sponsor: IMS
Abstract #304925 Presentation
Title: Conditions on Identifiability of Finite Mixtures of Truncated Poisson Distributions
Author(s): Mozhdeh Forghani* and Khalil Shafie
Companies: University of Northern Colorado and University of Northern Colorado
Keywords: Identifiability; Truncated Poisson; Probability generating function
Abstract:

A popular special case of the finite mixture models is a finite mixtures for the count data. For the case of multiple points of inflation in the small counts, where a clear theoretical relationship between small counts may exist, people have employed the finite mixtures of truncated Poisson distributions. For such models, the identifiability is an issue that must be addressed before any inference about parameters. In this work, based on Teicher's results on the identifiability of finite mixtures, by using the probability generating function, the conditions on identifiability for a finite mixtures of truncated Poisson distributions are studied.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program