An evaluation summary is automatically created when you are evaluating a regression model or a classification model.
The evaluation summary displays the name of the model, including the model type, the data table used in the model evaluation, and the model formula.
Additional summary statistics, appropriate for the particular model type are also shown. These statistics can give an indication of how good the model predicts the data and can also be used to compare model predictions against another model of the same type.
Summary Statistics
Regression Model |
Description |
R-squared (or R2) |
R-squared measures the fraction of the variability in the data that is explained by the model. It is a number between 0 and 1 with 1 being a perfect fit model (all observations are predicted exactly). |
SSE |
SSE, or Sum of Squares Error is the sum of the squared differences between the observed response and the predicted values from the models. |
Classification Model |
Description |
Accuracy |
The accuracy for a classification model is the fraction of values that are classified correctly by the model. Be careful when using this measure when the numbers in the classes are not balanced. |
Kappa |
Kappa is a measure of agreement for classification predictions that takes into account the agreement occurring by chance. Kappa takes on value between -1 (total disagreement) to 1 (total agreement). |
See also: