Identifying regions based on flexible user-defined constraints

Abstract

The identification of regions is both a computational and conceptual challenge. Even with growing computational power, regionalization algorithms must rely on heuristic approaches in order to find solutions. Therefore, the constraints and evaluation criteria that define a region must be translated into an algorithm that can efficiently and effectively navigate the solution space to find the best solution. One limitation of many existing regionalization algorithms is a requirement that the number of regions be selected a priori. The max-p algorithm, introduced in Duque et al. (2012), does not have this requirement, and thus the number of regions is an output of, not an input to, the algorithm. In this paper we extend the max-p algorithm to allow for greater flexibility in the constraints available to define a feasible region, placing the focus squarely on the multidimensional characteristics of region. We also modify technical aspects of the algorithm to provide greater flexibility in its ability to search the solution space. Using synthetic spatial and attribute data we are able to show the algorithm's broad ability to identify regions in maps of varying complexity. We also conduct a large scale computational experiment to identify parameter settings that result in the greatest solution accuracy under various scenarios. The rules of thumb identified from the experiment produce maps that correctly assign areas to their “true” region with 94% average accuracy, with nearly 50 percent of the simulations reaching 100 percent accuracy.

The internal structure of Greater London: a comparison of national and regional geodemographic models

“…Functional regional disaggregation of national extents (Folch and Spielman 2014), and compilation of geodemographics pertaining to their internal structure requires new thinking about how such models could be reassembled to enable cross-comparison. First, there is a need to address how we can balance the additional descriptive power of regional geodemographics relative to the loss of national comparability?…”

Spatial scale and small area population statistics for England and Wales

“…One approach is to determine internally homogeneous regions (e.g. Folch and Spielman 2014) which capture variation in the property of interest. Much previous work on scale change refers to images and focuses on optimal spatial resolutions (where cells in a coarser resolution image each contain the same number of cells at a finer resolution).…”

Reducing Uncertainty in the American Community Survey through Data-Driven Regionalization

“…The max- p is a heuristic optimization algorithm; Folch and Spielman (2014) [4] show that using an internal-variance-minimizing objective function like SSD finds the minimum-variance partition of the input map over 95 percent of the time. Areas are swapped iteratively, and each iteration tries to identify the best of all feasible swaps of a single tract between regions.…”