- Correlation means that two or more variables have some type of relationship.
- Causation indicates that one event is the result of the occurrence of another event, in other words, there is a casual relationship between the two events.
Tip
Correlation doesn’t imply causation. Correlation is easy to test but causation is almost impossible. A and B are correlated because some C exists such that C → A and C → B.
Example: Every time they light up the belt signal on the plane, it gets bumpy. The light signal and the bumpiness are correlated, but the light signal is not the cause of the bumpiness.
related: Correlation coefficient, Autocorrelation and Partial Autocorrelation, Multicollinearity tags:#ai/data-science