Late detection of breast and colorectal cancer in Minnesota counties: an application of spatial smoothing and clustering.

摘要: Cancers detected at a later disease stage are associated with significantly higher mortality risk. Lack of uniformity in county-level cancer detection rates is thus substantial interest to state health departments and other public professionals. In this paper, we perform several spatial analyses breast colorectal data for Minnesota counties 1995–1997. We look outliers clusters the late using number techniques: (i) applying various mapping schemes, (ii) smoothing Bayesian methods implemented via Markov chain Monte Carlo, (iii) maximum likelihood techniques test presence identify most likely clusters Our results suggest fairly uniform pattern both sets rates. Spatially smoothed did not reveal risk, nor were covariates (such as income, education, race) particularly helpful explaining However, our clustering approach (using scan statistic) produce statistically significant which may indicate differences practical importance health. Copyright © 2003 John Wiley & Sons, Ltd.