Automatic Region Building for Spatial Analysis

Abstract

High-resolution spatial data have become increasingly available with modern data collection techniques and efforts. However, it is often inappropriate to use the default geographic units to perform spatial analysis due to unstable estimates with small areas (e.g. cancer rates for census blocks or tracts). Regionalization is aggregating small units into relatively larger areas while optimizing a homogeneity measure (such as the sum of squared differences). For exploratory spatial analysis, regionalization may help remove spurious data variation through aggregation and discover hidden patterns in data (such as areas of unusually high cancer rates). Towards this goal, this research introduces several improvements to a recent group of regionalization methods -REDCAP (Guo 2008) and conducts evaluation experiments with synthetic data sets to assess and compare the capability of regionalization methods for exploratory spatial analysis. One of the major improvements is the integration of a local empirical Bayes smoother (EBS) with the regionalization methods. We generate a large number of synthetic data sets with controlled spatial patterns to evaluate the performance of both new and existing methods. Evaluation results show that the new methods (integrated with EBS) perform significantly better than their original versions and other methods (including the EBS method on its own) in terms of detecting the true patterns in the synthetic data sets.

Constructing geographic areas for cancer data analysis: A case study on late-stage breast cancer risk in Illinois

“…There are a number of automated regionalization methods reported in the literature that account for spatial contiguity and attribute homogeneity within the derived areas: the AZP (Openshaw 1977; Openshaw and Rao 1995; Cockings and Martin 2005; Grady and Enander 2009), MaxP (Duque et al, 2007), MSSC (Mu and Wang, 2008) and REDCAP (Guo 2008; Guo and Wang 2011). For example, the AZP method starts with an initial random regionalization and then iteratively refines the solution by reassigning objects to neighboring regions to improve the objective function value, and therefore the regionalization result varies dependent upon the initial randomization state.…”

Spatiotemporal aggregation for temporally extensive international microdata

“…One, research on regionalization, spatial regionalization in particular, is a fast expanding field and it will likely be necessary to revisit the underlying algorithmic basis for our semi-automated approach. Work on spatial regionalization is especially promising as applied to large data sets within a cyberinfrastructure setting, as well as continued improvements to existing algorithms (Diansheng Guo & Wang, 2011). Two, census geographies are always changing.…”

A column generation heuristic for districting the price of a financial product

“…Indeed, the main problem with hierarchical clustering is that the distance between two objects can be higher than the distance between the union of these objects and a third one. Recently, this method was adapted by Guo (2008) and improved later on by Guo and Wang (2011).…”