Apps

🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!

Modifiable Areal Unit Problem (MAUP)

Also Known As: Aggregation problem Spatial aggregation bias
Statistical Error ID: maup

Definition

The Modifiable Areal Unit Problem occurs when statistical results change depending on how geographic areas are defined or aggregated. The same underlying data can produce different correlations, patterns, and conclusions when analyzed at different spatial scales (the scale effect) or with different boundary placements (the zoning effect). This makes findings sensitive to arbitrary choices about spatial units rather than reflecting true relationships in the data.

Examples

An analysis of income and health outcomes at the county level shows a strong positive correlation. When the same data is re-aggregated at the state level, the correlation weakens substantially. At the census tract level, the correlation reverses in some areas. The finding depends entirely on which spatial unit the analyst chose.

A study mapping political party affiliation and median income shows a strong relationship when congressional districts are used as the unit of analysis. When the same voter and income data are reaggregated by ZIP code, the relationship reverses in several regions, because district boundaries were drawn in ways that grouped high- and low-income areas together.

Researchers analyzing air pollution exposure and asthma rates find a significant association at the city level. When they disaggregate the data to the neighborhood level, the association disappears in some areas and strengthens dramatically in others — reflecting how averaging pollution across a large city masks the intense local variation near industrial zones.

Verification Steps
Verification Steps
Binary yes/no questions that an AI must answer to detect a reasoning pattern in a text.
Each of the 452 aspects has verification steps — simple yes/no questions designed to systematically detect whether a pattern appears in a text. For ad hominem: "Does the argument attack a person rather than their claim?" For false dichotomy: "Are only two options presented when more exist?" This ensures consistent, reproducible analysis.

Binary (yes/no) questions an LLM must answer to identify this aspect:

  1. 1

    Does the analysis use data aggregated to geographic or spatial units?

    Type: binary
  2. 2

    Could changing the boundaries or size of these units alter the results?

    Type: binary
  3. 3

    Has the analysis been tested at multiple scales or with alternative boundary definitions?

    Type: binary
  4. 4

    Are conclusions drawn as if the chosen spatial units are the only valid way to analyze the data?

    Type: binary
Deep Dive
The expandable detail section on each aspect page with examples, psychology, and counter-strategies.
The Deep Dive section provides in-depth information about each aspect: a real-world example showing the pattern in action, an explanation of why it works psychologically, practical advice on how to counter it, alternative names, and links to related aspects.

Hierarchical Context