|
Activity Number:
|
619
- Spatial and Spatial-Temporal Statistics
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 2, 2018 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
|
Abstract #328709
|
Presentation
|
|
Title:
|
Bayesian Filtering and Model Calibration Approaches to Model an Epidemic Over Space and Time
|
|
Author(s):
|
David Higdon* and Arindam Fadikar and Jonathan Stroud
|
|
Companies:
|
Virginia Tech and Virginia Tech and Georgetown University
|
|
Keywords:
|
epidemic;
filtering;
Bayesian
|
|
Abstract:
|
Developing models that can predict flu cases throughout the United States over the course of a flu season brings up a number of challenges, especially if predictions are required at high spatio-temporal resolution. Challenges include: 1) modeling movement of individuals over the course of a day or week; 2) accounting for incomplete information on the number of cases reported by health providers; 3) accounting for high levels of aggregation in the case reporting; 4) accounting for inaccuracies in the movement modeling. We describe the application and give some approaches for giving real time predictions that leverage Bayesian filtering and model calibration methodology.
|
Authors who are presenting talks have a * after their name.
