Category-Specific Comparison of Univariate Alerting Methods for Biosurveillance Decision Support

摘要

We compared detection performance of univariate alerting methods on real and simulated events in different types of biosurveillance data. Both kinds of detection performance analysis showed the method based on Holt-Winters exponential smoothing superior on non-sparse time series with day-of-week effects. The adaptive CUSUM and Shewhart methods proved optimal on sparse data and data without weekly patterns.