April 1, 2021
Every way of using correlation as evidence for causality makes assumptions
Every way of using correlation as evidence for causality makes trade-off between:
Breaks \(W \rightarrow X\) link
|All confounding variables||\(X\) is random
Change only \(X\)
when we observe \(X\) and \(Y\) for multiple cases, we examine the correlation of \(X\) and \(Y\) within groups of cases that are the same on confounding variables \(W, etc. \ldots\)
How does conditioning solve confounding?
A few weeks back we asked:
data from Feinberg, Branton, and Martinez-Ebers
Correlation between Trump Rallies and Hate Crimes might suffer from confounding
Feinberg, Branton, and Martinez-Ebers compare hate crimes in counties with and without Trump rallies, but condition on (hold constant):
Feinberg, Branton, and Martinez-Ebers find that, even after conditioning, Trump rallies increase the risk of hate crimes by 200%!