Coefficient of Determination
The coefficient of determination, also known as and frequently notated as R2, is an expression of total variance captured by a regression.
Contents
Description
The total variation of a dependent variable (SST) can be decomposed as R2 = 1 - SSR/SST, where SSR is the sum of squared regression. R2 then represents how much of the total variation is explained by the regression.
In the context of multiple regression, it is guaranteed that R2 can only grow as predictors are added. This leads to the adjusted R2, which penalizes (through degrees of freedom) the inclusion of predictors that do not explain variation.