A Three-State Recursive Sequential Bayesian Algorithm for Biosurveillance K. D. Zamba a Panagiotis Tsiamyrtzis b Douglas M. Hawkins c a Department of Biostatistics, The University of Iowa, 200 Hawkins Drive, C22M GH Iowa City, IA 52242 b Department of Statistics, Athens University of Economics and Business; 76 Patission Str 10434 Athens Greece c School of Statistics, University of Minnesota, 313 Ford Hall, 224 Church Street Minneapolis, MN 55455 Abstract A serial signal detection algorithm is developed to monitor pre-diagnosis and medical diagnosis data pertaining to biosurveillance. The algorithm is three-state sequential, based on Bayesian thinking. It accounts for non-stationarity, irregularity, seasonality, and captures an epidemic serial structural details. At stage n, a trichotomous variable governing the states of an epidemic is defined, and a prior distribution for time-indexed serial readings is set. The technicality consists of finding a posterior state probability based on the observed data history, using the posterior as a prior distribution for stage n + 1 and sequentially monitoring surges in posterior state probabilities. A sensitivity analysis for validation is conducted and analytical formulas for the predictive distribu- tion are supplied for error management purposes. The method is applied to syndromic surveillance data gathered in the United States (U.S.) District of Columbia metropoli- tan area. Keywords: Bayesian Sequential Update, Dynamic Control, Syndromic Surveillance. 1 Introduction The problem that led to developing the method herein came from medical arena. Data pertaining to biosurveillance are used in the U.S. and in some countries around the globe to 1