Correlation is not causation
Also called: Cum hoc, Confusing correlation with cause
Assuming that two things which move together must have a cause-and-effect link.
How to spot it
Could a third factor drive both? Could the cause run the other way?
Example
“Ice cream sales and drownings rise together, so ice cream causes drowning.” (Both rise in summer.)
How to answer it
Ask what else could explain the link, and whether anyone tested it.
Related
- Post hoc: Assuming that because one thing followed another, the first caused the second.
- Single cause: Blaming one factor for something that has several causes.
- Cherry-picking: Showing only the evidence that supports your case, and leaving out the rest.
- Reverse causation: Assuming A causes B when B actually causes A.