The Modifiable Areal Unit Problem in Political Science

• In Event: Geography and Spatial Analysis

Abstract

Geography is now a central focus on political scientists in every subdiscipline. Building upon widespread availability of geospatial data, improvements in mapping software, and innovations in spatial statistics, political scientists are now taking geography seriously. As we adopt the tools of geographers, so too must we consider their methodological drawbacks. We focus on one such issue, the modifiable areal unit problem (MAUP)—the idea that the scale and zoning of our geographic units shape the empirical results we attain. We demonstrate different features of the MAUP in replications of articles in American Politics, Comparative Politics, and International Relations. In all cases, we show that the choice of units, whether zip codes, counties, commuting zones, or “random” gridcells, are susceptible to the MAUP. To conclude, we offer a range of options for scholars to assess sensitivity in their data and to overcome critiques on the basis of the MAUP.

Authors

• Melissa Ziegler Rogers, Claremont Graduate University

• Hillel David Soifer, Temple University

• Dong Wook Lee, Adelphi University