Evaluating spatial methods for investigating global clustering and cluster detection of cancer cases

Lan Huang, Linda Williams Pickle, Barnali Das

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

There have been articles on comparing methods for global clustering evaluation and cluster detection in disease surveillance, but power and sample size (SS) requirements have not been explored for spatially correlated data in this area. We are developing such requirements for tests of spatial clustering and cluster detection for regional cancer cases. We compared global clustering methods including Moran's I, Tango's and Besag-Newell's R statistics, and cluster detection methods including circular and elliptic spatial scan statistics (SaTScan), flexibly shaped spatial scan statistics, Turnbull's cluster evaluation permutation procedure, local indicators of spatial association, and upper-level set scan statistics. We identified eight geographic patterns that are representative of patterns of mortality due to various types of cancer in the U.S. from 1998 to 2002. We then evaluated the selected spatial methods based on state- and county-level data simulated from these different spatial patterns in terms of geographic locations and relative risks, and varying SSs using the 2000 population in each county. The comparison provides insight into the performance of the spatial methods when applied to varying cancer count data in terms of power and precision of cluster detection.

Original languageEnglish (US)
Pages (from-to)5111-5142
Number of pages32
JournalStatistics in Medicine
Volume27
Issue number25
DOIs
StatePublished - Nov 1 2008

Fingerprint

Cluster Detection
Cluster Analysis
Cancer
Scan Statistic
Clustering
Neoplasms
Spatial Clustering
Correlated Data
Relative Risk
Count Data
Requirements
Spatial Pattern
Evaluation
Geographic Locations
Clustering Methods
Level Set
Mortality
Surveillance
Permutation
Sample Size

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Statistics and Probability

Cite this

Huang, Lan ; Pickle, Linda Williams ; Das, Barnali. / Evaluating spatial methods for investigating global clustering and cluster detection of cancer cases. In: Statistics in Medicine. 2008 ; Vol. 27, No. 25. pp. 5111-5142.
@article{3499f28b1a604b178193cbb6a6a30a76,
title = "Evaluating spatial methods for investigating global clustering and cluster detection of cancer cases",
abstract = "There have been articles on comparing methods for global clustering evaluation and cluster detection in disease surveillance, but power and sample size (SS) requirements have not been explored for spatially correlated data in this area. We are developing such requirements for tests of spatial clustering and cluster detection for regional cancer cases. We compared global clustering methods including Moran's I, Tango's and Besag-Newell's R statistics, and cluster detection methods including circular and elliptic spatial scan statistics (SaTScan), flexibly shaped spatial scan statistics, Turnbull's cluster evaluation permutation procedure, local indicators of spatial association, and upper-level set scan statistics. We identified eight geographic patterns that are representative of patterns of mortality due to various types of cancer in the U.S. from 1998 to 2002. We then evaluated the selected spatial methods based on state- and county-level data simulated from these different spatial patterns in terms of geographic locations and relative risks, and varying SSs using the 2000 population in each county. The comparison provides insight into the performance of the spatial methods when applied to varying cancer count data in terms of power and precision of cluster detection.",
author = "Lan Huang and Pickle, {Linda Williams} and Barnali Das",
year = "2008",
month = "11",
day = "1",
doi = "10.1002/sim.3342",
language = "English (US)",
volume = "27",
pages = "5111--5142",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "25",

}

Evaluating spatial methods for investigating global clustering and cluster detection of cancer cases. / Huang, Lan; Pickle, Linda Williams; Das, Barnali.

In: Statistics in Medicine, Vol. 27, No. 25, 01.11.2008, p. 5111-5142.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluating spatial methods for investigating global clustering and cluster detection of cancer cases

AU - Huang, Lan

AU - Pickle, Linda Williams

AU - Das, Barnali

PY - 2008/11/1

Y1 - 2008/11/1

N2 - There have been articles on comparing methods for global clustering evaluation and cluster detection in disease surveillance, but power and sample size (SS) requirements have not been explored for spatially correlated data in this area. We are developing such requirements for tests of spatial clustering and cluster detection for regional cancer cases. We compared global clustering methods including Moran's I, Tango's and Besag-Newell's R statistics, and cluster detection methods including circular and elliptic spatial scan statistics (SaTScan), flexibly shaped spatial scan statistics, Turnbull's cluster evaluation permutation procedure, local indicators of spatial association, and upper-level set scan statistics. We identified eight geographic patterns that are representative of patterns of mortality due to various types of cancer in the U.S. from 1998 to 2002. We then evaluated the selected spatial methods based on state- and county-level data simulated from these different spatial patterns in terms of geographic locations and relative risks, and varying SSs using the 2000 population in each county. The comparison provides insight into the performance of the spatial methods when applied to varying cancer count data in terms of power and precision of cluster detection.

AB - There have been articles on comparing methods for global clustering evaluation and cluster detection in disease surveillance, but power and sample size (SS) requirements have not been explored for spatially correlated data in this area. We are developing such requirements for tests of spatial clustering and cluster detection for regional cancer cases. We compared global clustering methods including Moran's I, Tango's and Besag-Newell's R statistics, and cluster detection methods including circular and elliptic spatial scan statistics (SaTScan), flexibly shaped spatial scan statistics, Turnbull's cluster evaluation permutation procedure, local indicators of spatial association, and upper-level set scan statistics. We identified eight geographic patterns that are representative of patterns of mortality due to various types of cancer in the U.S. from 1998 to 2002. We then evaluated the selected spatial methods based on state- and county-level data simulated from these different spatial patterns in terms of geographic locations and relative risks, and varying SSs using the 2000 population in each county. The comparison provides insight into the performance of the spatial methods when applied to varying cancer count data in terms of power and precision of cluster detection.

UR - http://www.scopus.com/inward/record.url?scp=60249090294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60249090294&partnerID=8YFLogxK

U2 - 10.1002/sim.3342

DO - 10.1002/sim.3342

M3 - Article

VL - 27

SP - 5111

EP - 5142

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 25

ER -