Methods for Investigating Localized Clustering of Disease
Published on 27. March 1997
Book
Paperback/Softback
276 pages
978-92-832-2135-7 (ISBN)
Description
Since the beginning of this century, "clusters" of certain forms of cancer--particularly leukemia in children and Hodgkin's disease--have been reported around locations of specific environmental hazards. Identification of such clusters is not an easy task, since there is no exact definition of what a cluster is. This monograph describes the variety of statististical techniques cuurently in use, and their application to simulated data-sets chosen to represent a range of clustering scenarios. The scientists who developed these techniques were invited to apply their methodology to these data-sets and to share their conclusions in this volume. In addition, these researchers describe in complete detail how they proceeded with the analysis, since an element of subjectivity figures prominently in the application and interpretation of some of these methods. The identification and analysis of disease clusters can yield significant clues in epidemiologic research, and as such will continue to be an important subject of cancer research and epidemiology for the foreseeable future.
More details
Series
Language
English
Place of publication
Lyon
France
Target group
Professional and scholarly
Product notice
Paperback (trade)
Illustrations
tables, fig., col. ill.
1, black & white illustrations
Dimensions
Height: 254 mm
Width: 178 mm
Thickness: 15 mm
Weight
481 gr
ISBN-13
978-92-832-2135-7 (9789283221357)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Classification
Content
Foreword; Introduction; 1. Historical aspects of leukaemia clusters; 2. The simulated data -sets; 3. Analysing the spatial distribution of disease using a method of constructing geographical areas of approximately equal population size; 4. Testing for over-dispersion using an adapted form of the Potthoff-Whittinghill method; 5. Clustering methods based on k nearest neighbour distributions; 6. Using a geographical analysis machine to detect the presence of spatial clustering and the location of clusters in synthetic data; 7. The detection of small-area database anomalies; 8. Detailed results for selected data-sets; 9. Overview of results; 10. Editorial comments; 11. Responses by individual authors to editorial comments; APPENDICES; 1. The data-sets; 2. Extension of the ISD method; 3. Cuzick-Edwards one-sample and inverse two-sampling statistics; 4. Tests of clustering based on pattern-recognition procedures; 5. Second-order analysis of spatial clustering; 6. A scan statistic for detecting spatial clusters; 7. The CAS method; 8. Geostatistics for determining the risk of rare disease; References