Political Oddities

[Alcibiades]

Maybe someone has already done this, but I think an interesting project would be an analysis of how counties would be expected to vote based on their demographics (education, race, density, religiosity) versus how they actually vote.

If someone has a county dataset with e.g. 2020 election vote shares and that demographic data, then it should be pretty easy to run a regression of the former on the latter in, say, R and map the residual for each county.