Coefficient of determination (r²)

The coefficient of determination $r^2$ reports the share of the response's total variation that the least-squares line accounts for, so higher means a better linear fit. It is the square of the correlation coefficient $r$, and multiplying by 100 turns it into a percentage. For example, $r^2 = 0.64$ means 64% of the variation in the response is explained by the linear relationship with the explanatory variable, leaving 36% unexplained. Because it is a square, $r^2$ is never negative and never above 1.