Abstract Details
Activity Number:
|
28
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #312885
|
View Presentation
|
Title:
|
Confidence Intervals for the Odds Ratio Estimated from Count Models
|
Author(s):
|
Christopher Sroka*+ and Haikady Nagaraja
|
Companies:
|
Battelle and Ohio State University
|
Keywords:
|
Count models ;
odds ratio ;
confidence intervals ;
logistic regression
|
Abstract:
|
In many biomedical applications, researchers present and interpret their findings in terms of an odds ratio (OR) with respect to the presence versus absence of an event. When the data measure the frequency of an event, the count data is often converted into binary form (none versus at least one event) and well-established logistic regression procedures are used to obtain confidence intervals for the associated OR. However, such a data reduction results in information loss. This can be rectified if the count data are known to arise from a parametric model. In this work, we discuss likelihood based inference for odds ratios using data from common count models. Our results make use of known properties of estimators from these models, including the asymptotic normality of maximum likelihood estimators. We illustrate the applications of our results and compare the confidence intervals obtained from the complete data and from its compressed version.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.