期刊名称：Human Geographies : Journal of Studies and Research in Human Geography
印刷版ISSN：1843-6587
电子版ISSN：2067-2284
出版年度：2012
卷号：6
期号：2
页码：5-13
出版社：University of Bucharest
摘要：Type II diabetes is a growing health problem in the United States. Understanding geographic variation in diabetes prevalence will inform where resources for management and prevention should be allocated. Investigations of the correlates of diabetes prevalence have largely ignored how spatial nonstationarity might play a role in the macro-level distribution of diabetes. This paper introduces the reader to the concept of spatial nonstationarity¡ªvariance in statistical relationships as a function of geographical location. Since spatial nonstationarity means different predictors can have varying effects on model outcomes, we make use of a geographically weighed regression to calculate correlates of diabetes as a function of geographic location. By doing so, we demonstrate an exploratory example in which the diabetes-poverty macro-level statistical relationship varies as a function of location. In particular, we provide evidence that when predicting macro-level diabetes prevalence, poverty is not always positively associated with diabetes
