In statistics, an ecological correlation (also spatial correlation) is a correlation between two variables that are group means, in contrast to a correlation between two variables that describe individuals.[1] For example, one might study the correlation between physical activity and weight among sixth-grade children. A study at the individual level might make use of 100 children, then measure both physical activity and weight; the correlation between the two variables would be at the individual level. By contrast, another study might make use of 100 classes of sixth-grade students, then measure the mean physical activity and the mean weight of each of the 100 classes. A correlation between these group means would be an example of an ecological correlation.
Because a correlation describes the measured strength of a relationship, correlations at the group level can be much higher than those at the individual level. Thinking both are equal is an example of ecological fallacy.[2]
See also
[edit]- General topics
- Ecological regression
- Geographic information science
- Spatial autocorrelation
- Complete spatial randomness
- Modifiable areal unit problem
- Specific applications
References
[edit]- ^ Robinson, W. S. (1950). "Ecological Correlations and the Behavior of Individuals". American Sociological Review. 15 (3): 351–357. JSTOR 2087176.
- ^ Vogt, W. Paul; Johnson, R. Burke (2011). Dictionary of Statistics & Methodology: A Nontechnical Guide for the Social Sciences. Sage. p. 119. ISBN 978-1-4522-3659-9.