Abstract:
|
Public health surveillance systems are used to detect and locate clusters of cases of diseases in space-time, indicating the possible occurrence of outbreaks. A methodology based on adaptive likelihood ratios (ALRs) to the detection of an emerging disease cluster is presented. It preserves the martingale structure of the regular likelihood ratio, allowing the determination of an upper limit for the false alarm rate, depending only on the quantity of evaluated cluster candidates. A fast computational algorithm incorporates this property, determining the cutting point to control the false alarm rate. Consequently, Monte Carlo simulations are not required to validate the procedure's statistical significance. The greater flexibility of the candidate clusters' shape produces a better estimation of the most likely cluster. An adaptive approach is also built for the clusters' configuration space to avoid the large cardinality of the collection of candidates. Performance is evaluated through simulations to measure the average detection delay and the probability of correct cluster detection. An application is shown for thyroid cancer in New Mexico.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.