Abstract Details
Activity Number:
|
314
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 6, 2013 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Bayesian Statistical Science
|
Abstract - #308121 |
Title:
|
Predicting Rare Events in the Presence of Zero-Inflation and Covariate Misclassification: A Bayesian Approach
|
Author(s):
|
MaryAnn Morgan-Cox*+ and James D. Stamey and John W Seaman, Jr
|
Companies:
|
Eli Lilly and Company and Baylor University and Baylor University
|
Keywords:
|
zero-inflation ;
Poisson regression ;
misclassification ;
simulation ;
Bayesian modeling ;
rare event
|
Abstract:
|
In healthcare research, outcomes of interest often consist of count variables. For such counts, the Poisson regression model is commonly used to explain the relationship between the outcome and a set of explanatory variables. However, it is often the case that there is a higher proportion of zero counts than would be predicted by the Poisson distribution, possibly due to a distinct subpopulation of subjects whose only response is zero counts. To adjust for extra zero counts, we investigate a Bayesian zero-inflated Poisson model, where we extend the previous models to account for misclassification of previous treatment failure. Suppose the outcome of interest is the number of adverse events related to a prescribed treatment. Patients who are at small risk have zero complications. Patients who are at a higher risk will exhibit Poisson distributed-numbers of complications. By accounting for both the underlying zero state and the probability of treatment failure misclassification, we ascertain a more accurate prediction (and earlier signal detection) of this rare adverse event. Performance of the model is assessed via simulation study and case example.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education 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.