Sampling for Region-Aggregated Spatial Scan Statistics
For practitioners in GIS and public health using tools like SaTScan, this provides a simple fix to a known bottleneck—loss of power from centroid-based aggregation—without requiring new algorithms.
The paper addresses the loss of statistical power when applying point-based spatial scan statistics to region-aggregated data (e.g., census tracts) by collapsing regions to centroids. They propose sampling 20-50 points uniformly from each region's geometry and spreading values evenly, which improves statistical power while maintaining computational tractability.
Anomaly detection in geospatial data is a crucial tool in geographic information science (GIS), with applications ranging from national security to public-health surveillance to the study of societal disparities. This work focuses on spatial scan statistics and addresses a key mismatch: spatial counts are typically aggregated into predefined regions (census tracts, zip codes, counties), whereas the most efficient scan algorithms operate on spatial point data. The standard remedy -- collapsing each region to its centroid, as in widely used tools such as SaTScan -- is convenient but, as we show, discards the region's spatial extent and causes a significant loss in statistical power. To resolve this, we propose a simple yet scalable fix: replace each spatial region with 20-50 points sampled uniformly from its geometry and spread the region's values evenly across them. This approach improves statistical power while maintaining computational tractability. A convergence analysis explains why so few samples per region suffice. We recommend this sampling-based conversion as the default way to apply point-based spatial scan statistics to region-aggregated data for anomaly detection.