probability

If A and B are correlated, A causes B, or B causes A, or they share a latent common cause

David Ellis

Jul 1, 2020 • 1 min read

An Introduction to Causal Discovery, a Bayesian Network Approach from COST action BM1006

"According to Reichenbach's principle, a correlation between two variables x and y can arise either because x is a cause of y, y is a cause of x, or both share a (possibly unobserved, i.e. latent) common cause h."
- Page 41 of Allison, B. Z., Guger, C. (2013). Brain-Computer Interface Research: A State-of-the-Art Summary. Germany: Springer Berlin Heidelberg.

Relevant xkcd:

Correlation doesn't imply causation, but it does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there'.