Activity Number:
|
146
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 7, 2006 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Epidemiology
|
Abstract - #305532 |
Title:
|
Modeling and Prediction of Influenza Outbreaks Using Chest Radiograph Data
|
Author(s):
|
Peter F. Craigmile and Namhee Kim and Soledad Fernandez*+ and Bema Bonsu
|
Companies:
|
The Ohio State University and The Ohio State University and The Ohio State University and Columbus Children's Hospital
|
Address:
|
320 W. 10th Ave., Columbus, OH, 43221,
|
Keywords:
|
one step prediction errors ; filtering ; alarm processes ; regression models ; seasonal autoregressive moving average models
|
Abstract:
|
We apply time-series methods to the modeling and prediction of influenza outbreaks using chest radiograph data in children's emergency departments. These models incorporate available covariate information, such as (possibly smoothed) visit counts and temperature series, as well as time-series dependencies on daily and weekly seasonal scales. Outbreaks detection is based on filtering the one-step-ahead prediction errors obtained from these time-series models. Using simulation experiments, we illustrate the effect of the choice of filter and the statistical models on outbreak detection.
|