Cluster Detection Incorporating Lagged Test Data

Using New York Cityís dead bird surveillance for West Nile Virus (WNV), this paper presents two explorations of the spatial cluster detection problem in which lagged test results are available for a random subset of observations. First, we establish a framework for the direct evaluation of methods and identify the optimal parameterization over a large family of models. We then investigate ways in which the lagged test results and other covariates might be used prospectively to extend the family of models by refining the baseline.