{
  "abstract": "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 divide the region's measured and baseline counts evenly among 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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Proc. 34th ACM SIGSPATIAL Int. Conf. on Advances in Geographic Information Systems (SIGSPATIAL '26), 2026",
  "arxiv": "2607.01451",
  "author_total": 4,
  "authors": [
    {
      "name": "Foad Namjoo"
    },
    {
      "name": "Drew McClelland"
    },
    {
      "name": "Michael Matheny"
    },
    {
      "name": "Jeff M. Phillips"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/djyj9560vyx3z.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.01451",
  "fulltext_url": null,
  "id": "djyj9560vyx3z",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.01451",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CG"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "openalex",
      "2713|Data-Driven Disease Surveillance"
    ]
  ],
  "openalex": "W7167252995",
  "pdf_url": "https://arxiv.org/pdf/2607.01451",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/djyj9560vyx3z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:54Z",
      "native_id": "2607.01451",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.01451"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Sampling for Region-Aggregated Spatial Scan Statistics",
  "title_text": "Sampling for Region-Aggregated Spatial Scan Statistics",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:54Z",
  "url": "https://research.draconitic.com/paper/djyj9560vyx3z",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1145/3841645.3842988",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}