No. 258 · Evidence · Statistics and Probability
Correlation and Causation
Patterns are where good questions begin, not where they end.
In the Almanac
“Doll and Hill”, 1950–1965 · “Kellogg’s”, 2009
Both stories in full, three ways to use it and where it misleads.
Get the AlmanacListen · Watch
Questions
What is Correlation and Causation?
Correlation and causation are not the same. Two things can move together because of coincidence, a hidden third factor or cause running the other way. Proving cause takes stronger evidence, like strength, consistency and dose-response.
How do you use Correlation and Causation?
To use it, question headlines that link habits to outcomes, test new ideas with fair trials before scaling, and ask marketers for real evidence of effect.
When does Correlation and Causation matter?
Correlation and Causation is one of the 68 mental models for evidence, the situations where you ask: Is this really true? Within that, it belongs to “Cause or coincidence?”, alongside Causal Fallacy, Clustering Illusion and Confounding Factor.
What is an example of Correlation and Causation?
Two stories show it at work: Doll and Hill (1950–1965) and Kellogg’s (2009). Both are told in full in The Mental Models Daily Almanac, which has two stories for each of its 365 models.
Which mental models are related to Correlation and Causation?
Confounding Factor, Causal Fallacy and A/B Testing. Correlation and Causation itself comes from statistics and probability.