A Spatial‐EWMA Framework for Detecting Clustering

• DOI: 10.1002/qre.1484
• Publication Date: 2013-01-16T12:14:59Z
• Authors: Chen‐ju Lin; Kwok‐Leung Tsui; Chen‐yu Lin
• Keywords: 0101 mathematics; 01 natural sciences; 3. Good health

Spatial surveillance is critical to health systems, manufacturing industries, and in many other domains. For example, determining hotspots of infectious diseases detecting defect patterns on semiconductor wafers require sensitive spatial analysis tools. The goal this paper detect clusters with mean shifts. Conventional multivariate methods may ignore structure among data lead inefficient inspection. Several likelihood ratio‐based scan statistics have been designed for surveillance. However, there no most powerful test when parameters like shift magnitude coverage are unknown. This proposes a exponentially weighted moving average (spatial‐EWMA) approach that can the existence locate potential centers clusters. procedure assigns different weights radius levels from investigated center. efficiency spatial‐EWMA shown by simulation. Lastly, an example counties high incidence male thyroid cancer New Mexico provided show effectiveness proposed approach. Copyright © 2013 John Wiley & Sons, Ltd.