I originally wrote this article in 2014 to discuss whether correlation implies causation. Not that I expect everyone to read and remember this one article, but it’s frustrating when I see a conversation where people who deny science and accept science both misuse correlation and how it relates to causation. So, I decided to update this article and republish it as a reminder that the relationship of correlation to causation isn’t as easy as a simple trope or meme.
One of the foundations of biomedical science is whether correlation implies causation. Anti-vaccine activists often conflate or misunderstand the two, rejecting or accepting correlation as it fits its narrative. The “correlation implies causation” story is often abused, misused and confused by many writers.
One thing we do know about correlation is that if you can’t establish correlation, despite numerous attempts, it is nearly impossible to claim causation. Also, if you do observe correlation, it also doesn’t imply causation.
But there are methods, grounded in powerful science, to establish causation from observations of correlation. So sometimes correlation does not imply causation. But sometimes correlation implies causation.
This article will help show how we may be able to establish causation from observations of correlation. And, like all science, this is hard stuff. Continue reading “Correlation implies causation – when it does or does not with vaccines”