You are not currently logged in.
Access JSTOR through your library or other institution:
Use of the Spatial Scan Statistic to Identify Geographic Variations in Late Stage Colorectal Cancer in California (United States)
Lori A. Pollack, Carol A. Gotway, Janet H. Bates, Arti Parikh-Patel, Thomas B. Richards, Laura C. Seeff, Holly Hodges and Sidibe Kassim
Cancer Causes & Control
Vol. 17, No. 4 (May, 2006), pp. 449-457
Published by: Springer
Stable URL: http://www.jstor.org/stable/29736480
Page Count: 9
You can always find the topics here!Topics: Colorectal cancer, Cancer, Epidemiology, Socioeconomic status, Disease risks, Cancer screening, Statistics, Breast cancer, Geographical variation, Delayed diagnosis
Were these topics helpful?See somethings inaccurate? Let us know!
Select the topics that are inaccurate.
Preview not available
Preview not available
Objectives To identify geographic variations in colorectal cancer by stage at diagnosis in California using a descriptive analysis coupled with a spatial analysis and to discuss methodological considerations concerning the spatial statistical method. Methods We analyzed 59,076 colorectal cancer cases diagnosed in California from 1996 to 2000 by logistic regression and by a spatial scan statistic to identify areas with a higher and lower relative risk of late-stage colorectal cancer. Results In California, 57% of overall cases of colorectal cancer were diagnosed at a late stage. Californians diagnosed with late-stage colorectal cancer were more likely to be Hispanic and living in areas of lower socioeconomic status. The spatial scan identified two areas where the observed number of late-stage cancer was different than the number expected from the distribution in the rest of the state. Conclusions Spatial scan analyses can complement descriptive statistics, but results must be interpreted with consideration of factors that affect the ability to detect meaningful differences such as the number of events observed, accuracy in geocoding rural versus urban addresses, and the difficulty of adjusting for covariates.
Cancer Causes & Control © 2006 Springer