Recorded presentation

Al Ozonoff, PhD, Marco Bonetti, PhD, Laura Forsberg, and Marcello Pagano, PhD. Department of Biostatistics, Harvard School of Public Health, 655 Huntington Avenue, Boston, MA 02115, 617-432-2416, aozonoff@hsph.harvard.edu

Typically, statistical analysis of surveillance data has focused on univariate test statistics for spatial, temporal, or spatio-temporal surveillance. This approach ignores the possibility that clustering occurs in both time and space simultaneously. Here we propose a bivariate method that utilizes both the temporal and the spatial information from data that might be routinely available for surveillance purposes. We discuss our approach, evaluate its utility as it would be applied in a syndromic surveillance setting, and discuss further methodological developments in the area of surveillance.

Learning Objectives:

• We define and discuss the important differences between univariate and bivariate methods in spatio-temporal surveillance.

Keywords: Surveillance, Bioterrorism

Presenting author's disclosure statement:
I do not have any significant financial interest/arrangement or affiliation with any organization/institution whose products or services are being discussed in this session.

Recorded presentation