Content deleted Content added
m Adding category Category:Least squares (using HotCat) |
touch up |
||
Line 1:
{{Unreferenced|date=February 2007}}
In [[statistics]], the '''fraction of variance unexplained (FVU)''' in the context of a [[Regression analysis|regression task]] is the
For a more general definition of explained/unexplained variation/randomness/variance, see the article [[explained variation]].
Line 12:
\end{align}</math>
where ''R''<sup>2</sup> is the [[coefficient of determination]], and ''SS''<sub>''E''</sub> (the sum of squared predictions errors, equivalently the [[residual sum of squares]]), ''SS''<sub>''T''</sub> (the [[total sum of squares]]), and ''SS''<sub>''R''</sub> (the sum of squares of the regression, equivalently the [[explained sum of squares]]) are given by
:<math>\begin{align}
Line 28:
==Explanation==
It is useful to consider the second definition to get the idea behind FVU. When trying to predict ''Y'', the most naïve regression function that we can think of is the constant function predicting the mean of ''Y'', i.e., <math>f(x_i)=\bar{y}</math>. It follows that the MSE of this function equals the variance of ''Y''; that is, ''SS<sub>E</sub>'' = ''SS<sub>T</sub>'', and ''SS<sub>R</sub>'' = 0. In this case,
==See also==
|