Collaborative Research Developing ATD Bayesian Methods in Syndromic Surveillance: CAR Models and Computational Implementation

This research project focuses on the probability that a particular disease is present somewhere in the US, or present in a particular city, together with the associated uncertainty. There is enormous social benefit from early discovery of disease. The stakes are immense. The latest swine flu epidemic is a great example of how quickly a disease can begin and spread around the world.

The intellectual merit of the research on statistical theory and methodology is its addressing a range of challenges, including scalability, complex dependences in the data, covariates, temporal and spatial variations and low quality data. The unifying theme is principled calculation of uncertainties. Impact and merit merge especially sharply in the focus on usability by decision-makers, including detailed attention to false positives.

Team members are based at five institutions in the southeastern US: Clemson University, Duke University, The University of Georgia, The University of South Carolina and the National Institute of Statistical Sciences. NISS is the lead institution: Alan Karr, Director of NISS and Principal Investigator for the proposal, has extensive experience in assembling and managing large-scale, geographically distributed collaborations. The group will employ multiple modes of collaboration, including face-to-face meetings, video conferencing and tele/data-conferencing. Two new researchers - one postdoctoral fellow and one graduate student - will acquire unique collaborative skills and experience.