Authors: Nicholas Bogen*, Central Michigan University
Topics: Cartography, Geographic Information Science and Systems, United States
Keywords: Affinity Propagation,Tessellation
Session Type: Poster
Start / End Time: 9:55 AM / 11:35 AM
Room: Lincoln 2, Marriott, Exhibition Level
Presentation File: No File Uploaded
The United States is characterized by its socio-economic diversity. The identification, analysis and visualization, of ‘regions’ is a prominent challenge in geography, especially using data with high-dimensionality. In this poster, I have mapped 11 socio-economic clusters that are based on 40 attributes from the US census data and calculated using the statistical clustering algorithm Affinity Propagation, which considers all data points as potential exemplars of the socio-economic clusters. The mapping of this data presents its own challenges including the number of qualitative classes and issues of spatial scale using zip code tabulation areas. Using a square tessellation (i.e. fishnet), the exemplars were converted into equal-area gridded data that allows for uniformity in spatial scale and improved visualization. Inset maps of each cluster, labeled with the exemplar zip code tabulation area, were also created to highlight and compare individual clusters. The results highlight multiple socio-economic patterns in the United States including urban/suburban/rural regionalization, as well as patterns related to race and ethnicity and migration in the Southeast, Southwest, and urban areas in the Midwest.