Exploring Statistical Correlation: Causation and Non-Linearity

Statistical Analysis  »  Exploring Statistical Correlation: Causation and Non-Linearity


What does it mean that two variables are correlated? In this video, we explore the meaning of correlation and remind you that, as the old adage says, correlation does not equal causation.

Two variables may appear to be correlated when, in fact, they are unrelated, and the apparent correlation is the result of random chance. This is called a spurious correlation. Two variables may also be correlated if they share a similar cause, although neither one causes the other.

Moreover, two variables may be non-linearly correlated, meaning the correlation is neither purely positive nor purely negative. In these cases, special consideration must be given to the statistical handling of the non-linear relation between the two variables.


Leave a Reply

Your email address will not be published. Required fields are marked *