Ecological regression

{{Short description|Statistical technique}}

{{More citations needed|date=March 2021}}

Ecological regression is a statistical technique which runs regression on aggregates, often used in political science and history to estimate group voting behavior from aggregate data.{{Cite journal |last=Gelman |first=Andrew |last2=Park |first2=David K. |last3=Ansolabehere |first3=Stephen |last4=Price |first4=Phillip N. |last5=Minnite |first5=Lorraine C. |date=2001 |title=Models, assumptions and model checking in ecological regressions |url=http://www.stat.columbia.edu/~gelman/research/published/ecological.pdf |journal=Journal of the Royal Statistical Society, Series A (Statistics in Society) |volume=164 |issue=1 |pages=101–118 |doi=10.1111/1467-985x.00190 |issn=0964-1998}}

For example, if counties have a known Democratic vote (in percentage) D, and a known percentage of Catholics, C, then running a linear regression of dependent variable D against independent variable C will give D = a + bC. If the regression gives D = .22 + .45C for example, then the estimated Catholic vote (C = 1) is 67% Democratic and the non-Catholic vote (C = 0) is 22% Democratic. The technique has been often used in litigation brought under the Voting Rights Act of 1965 to see how blacks and whites voted.{{cite book|author=Jacob S. Siegel|title=Applied Demography: Applications to Business, Government, Law and Public Policy|url=https://books.google.com/books?id=a5Ax1oRbkDMC&pg=PA557|year=2002|publisher=Emerald Group |page=557|isbn=9780126418408}}