All spatial data is not created equal.
Dr. Tony Grubesic, an Arizona State University professor, has called them “one of the quirkier ‘geographies’ in the world.” Dr. Nancy Krieger, a Harvard University professor, and colleagues have called out their unacceptability for small-area analyses.
The article is a valuable case study in why scale appropriate data is critical for teasing out spatial patterns. While ZIP codes do have a place in analytics, the use of this level of data to look at Flint’s lead contamination issue was not.
This map produced by Sadler shows how ZIP codes don’t align with the boundaries of the city of Flint or its municipal water system. As Sadler notes:
One-third of all homes with a Flint ZIP code lie outside the city. Thus, the state’s numbers for Flint were watered down by an additional 50 percent of addresses that weren’t in the city and weren’t using Flint water. This is referred to in geography as the modifiable areal unit problem.
(via Rob Simmon)