The effects of scale on tests for disease clustering.

Surveillance of a large geographic region for 'clusters' of adverse health events, particularly cancers, often involves searching for raised incidence in the vicinity of prespecified putative sources of hazard. For reasons of practicality or of confidentiality, incidence and population data are usually only available aggregated over subregions or 'cells'. The performance of statistical procedures designed to detect the presence of clusters can be highly sensitive to the level of aggregation, that is to the choice of partition of the region into the cells. We investigate this sensitivity in the cases of three recently proposed procedures, namely those of Besag and Newell, Stone, and Waller et al. For illustration, we use leukaemia incidence data for 1978-82 in a region of upstate New York, with inactive hazardous waste sites containing trichloroethylene acting as suspected sources.

[1]  Bradley P. Carlin,et al.  Bayes methods in the ecological fallacy context: Estimation of individual correlation from aggregate data , 1990 .

[2]  N. Breslow.  Extra‐Poisson Variation in Log‐Linear Models , 1984 .

[3]  S. C. Darby,et al.  Geographical variation in mortality from leukaemia and other cancers in England and Wales in relation to proximity to nuclear installations, 1969-78. , 1989, British Journal of Cancer.

[4]  T. Wheldon,et al.  The assessment of risk of radiation-induced childhood leukaemia in the vicinity of nuclear installations , 1989 .

[5]  Richard Wakeford,et al.  Childhood Leukaemia and Nuclear Installations , 1989 .

[6]  R. A. Stone.  Investigations of excess environmental risks around putative sources: statistical problems and a proposed test. , 1988, Statistics in medicine.

[7]  S. Openshaw.  Ecological Fallacies and the Analysis of Areal Census Data , 1984, Environment & planning A.

[8]  A. Laplanche,et al.  Overall mortality and cancer mortality around French nuclear sites , 1990, Nature.

[9]  J F Bithell,et al.  On statistical methods for analysing the geographical distribution of cancer cases near nuclear installations. , 1989, Journal of epidemiology and community health.

[10]  C. E. Gehlke,et al.  Certain Effects of Grouping upon the Size of the Correlation Coefficient in Census Tract Material , 1934 .

[11]  Roger Marshall,et al.  A Review of Methods for the Statistical Analysis of Spatial Patterns of Disease , 1991 .

[12]  A. Polednak,et al.  Lung cancer in relation to residence in census tracts with toxic-waste disposal sites: a case-control study in Niagara County, New York. , 1989, Environmental research.

[13]  M. Monmonier.  How to Lie with Maps , 1991 .

[14]  R. C. Larson.  THE INVALIDITY OF MODIFIABLE AREAL UNIT RANDOMIZATION , 1986 .

[15]  D W Merrill,et al.  Density equalized map projections: a method for analysing clustering around a fixed point. , 1988, Statistics in medicine.

[16]  B. Turnbull,et al.  Monitoring for clusters of disease: application to leukemia incidence in upstate New York. , 1990, American journal of epidemiology.

[17]  Marvin Zelen,et al.  An Analysis of Contaminated Well Water and Health Effects in Woburn, Massachusetts , 1986 .

[18]  R. Haining.  Spatial Data Analysis in the Social and Environmental Sciences , 1990 .

[19]  P. Diggle.  A point process modeling approach to raised incidence of a rare phenomenon in the vicinity of a prespecified point , 1990 .

[20]  B. Turnbull,et al.  Chronic disease surveillance and testing of clustering of disease and exposure: Application to leukemia incidence and TCE‐contaminated dumpsites in upstate New York , 1992 .

[21]  Noel A Cressie,et al.  Statistics for Spatial Data. , 1992 .

[22]  P. Ewings,et al.  Incidence of leukaemia in young people in the vicinity of Hinkley Point nuclear power station, 1959-86. , 1989, BMJ.

[23]  J. Viel,et al.  Childhood leukaemia around the La Hague nuclear waste reprocessing plant. , 1990, BMJ.

[24]  A. Craft,et al.  INVESTIGATION OF LEUKAEMIA CLUSTERS BY USE OF A GEOGRAPHICAL ANALYSIS MACHINE , 1988, The Lancet.

[25]  Stan Openshaw,et al.  A geographical solution to scale and aggregation problems in region-building, partitioning and spatial modelling , 1977 .

[26]  Julian Besag,et al.  The Detection of Clusters in Rare Diseases , 1991 .

[27]  Richard Doll,et al.  The Epidemiology of Childhood Leukaemia , 1989 .

[28]  Martin J. Gardner,et al.  Review of Reported Increases of Childhood Cancer Rates in the Vicinity of Nuclear Installations in the Uk , 1989 .

[29]  D Hémon,et al.  Comparison of relative risks obtained in ecological and individual studies: some methodological considerations. , 1987, International journal of epidemiology.

[30]  Roger C. Grimson,et al.  The clustering of disease , 1979 .

[31]  Norman E. Breslow,et al.  Multiplicative Models and Cohort Analysis , 1983 .