|
Activity Number:
|
371
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305005 |
|
Title:
|
Choosing a Variance Function in Semiparametric Analysis of Overdispersed Count Data
|
|
Author(s):
|
Sudhir R. Paul*+
|
|
Companies:
|
University of Windsor
|
|
Address:
|
401 Sunset Avenue, Windsor, ON, N9B 3P4, Canada
|
|
Keywords:
|
Dispersion parameter ; Extended quasi-likelihood ; Negative binomial (NB) model ; Three parameter NB Model ; Variance function
|
|
Abstract:
|
The purpose of this paper is to determine an appropriate variance function (mean-variance relationship) which can be used in the semiparametric analysis of over-dispersed count data. We use hypothesis testing approach through a broader class of models and data analytic approach. The models considered are the three parameter negative binomial distribution and the extended quasi-likelihood. Wide analysis involving tests, data analysis and simulations show superiority of the variance function Var(Y)=cµ
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
