Journal Archives

Contiguity principle for geographic units: evidence on the quantity, degree, and location of Public Use Microdata Area (PUMA) fragmentation

Author: and

Social scientists investigating how context varies by geographical location and/or how macro-level phenomenon affects individual outcomes often make use of U.S. Census Bureau Public Use Microdata Sample (PUMS) files where micro-units can only be geographically located to Public Use Microdata Area (PUMA) polygons. Most spatial analysis investigations with PUMAs ignore the fact that many of them are multipart polygons—spatially separated polygons that share the same attribute and are stored as a single feature in a vector file. We briefly discuss the theoretical premises of how geo-graphical boundaries are created for macro units and investigate the quantity, degree, and location of PUMA fragmenta-tion. We argue that the basic contiguity principle (the assumption that spatial analysis uses polygon centroids for solid and contiguous geographic units) in spatial dependence analysis is being violated with many PUMAs in the U.S. mainland—where Texas, California, Tennessee, and Illinois merit special attention. Future research should outline a method for handling multipart polygons in spatial and hierarchical analyses.

Keywords: , , , , ,
Issue: Volume 7, Issue 2, 2013

An Introduction to Macro-Level Spatial Nonstationarity: A Geographically Weighted Regression Analysis of Diabetes and Poverty

Author: , and

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—variance 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.

Keywords: , , , , ,
Issue: Volume 6, Issue 2, 2012