|
Activity Number:
|
525
- Contributed Poster Presentations: Transportation Statistics Interest Group
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 2, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Transportation Statistics Interest Group
|
|
Abstract #324569
|
|
|
Title:
|
Modeling Overdispersed Count Data with the Poisson-Inverse Gaussian Distribution
|
|
Author(s):
|
Kimberly Weems* and Paul Smith
|
|
Companies:
|
North Carolina Central University and University of Maryland
|
|
Keywords:
|
overdispersion ;
robustness ;
count data ;
Poisson-inverse Gaussian ;
influence function
|
|
Abstract:
|
Count data arise in a variety of situations and are often modeled with a Poisson distribution. In many cases, however, the data do not satisfy the Poisson distribution's property of equal mean and variance. This project will examine the Poisson-inverse Gaussian (P-IG) distribution that accounts for overdispersion. The main goal of this project is to determine the robustness of maximum likelihood estimators when the inverse Gaussian distribution is misspecified. Results from a simulation study and applications to real data will be presented.
|
Authors who are presenting talks have a * after their name.
