Space-Time Surveillance Of Count Data Subject To Linear Trends

This paper proposes a new space-time cumulative sum (CUSUM) approach for detecting changes in spatially distributed Poisson count data subject to linear drifts. We develop expressions for the likelihood ratio test monitoring statistics and the change point estimators. The effectiveness of the proposed monitoring approach in detecting and identifying trend-type shifts is studied by simulation under various shift scenarios in regional counts. It is shown that designing the space-time monitoring approach specifically for linear trends can enhance the change point estimation accuracy significantly. A case study for male thyroid cancer outbreak detection is presented to illustrate the application of the proposed methodology in public health surveillance.