Correlation

Also known as: Pearson correlation, Correlation coefficient

Correlation (Pearson) standardises covariance:

\[\mathrm{Cor}(X,Y)=\frac{\mathrm{Cov}(X,Y)}{\sigma_X\sigma_Y}\in[-1,1].\]

$\pm 1$ means perfect linear relationship; $0$ means no linear association (nonlinear dependence can remain). Sample correlation uses sample SD and covariance. High correlation is not causation — regression inference still needs a model and assumptions.

← Back to CS Glossary