There are three measures of variation in a Linear Regression model that determine — “ how much of the variation in Y (the dependent variable/output variable) could be explained by the variation in X (the independent variable/input variable) ”.
- Regression Sum of Squares - SSR
SSR quantifies the variation that is due to the relationship between X and Y. This can also be thought of as the explained variability in the model, ie., the variation explained by the input variable X.
Interpretation: The SSR is equal to the summation of squared differences between the predicted Y values (using the regression equation from our model) and the mean value of Y.
2. Error Sum of Squares - SSE
SSE quantifies the variation that is due to (other) factors, apart from the relationship between X and Y. This can be thought of as the unexplained variability in the model, ie., the amount of variability that is not explained by the input variable X.
Interpretation: The SSE is equal to the summation of squared differences between the observed Y values and the predicted Y values (using the regression line from our model).
