The sum of squares for regression can never be larger than the sum of squares for error.

Question

Quizplus · Accepted Answer

The sum of squares for regression represents the variability that the regression model is able to explain, while the sum of squares for error represents the variability that the regression model is unable to explain. Therefore, it is possible for the sum of squares for error to be larger than the sum of squares for regression, particularly if the model has poor fit.

The Sum of Squares for Regression Can Never Be Larger