Creates a new variable containing predicted values for each case in the data from a machine learning model. Observations with missing values in the predictors are predicted as NA.
A predictive model such as regression, linear discriminant, random forest or any other machine learning model generated in Q.
To save the predicted values:
- Select the machine learning model output.
- Select Create > Classifier > Save Variable(s) > Predicted Values.
A table of categorical predictions is generated:
Uses the predict method from R. Unlike the defaults in most R packages, this implementation assigns predicted values for observations not in the estimation sample. Categorical variables are predicted as discrete.
Article is closed for comments.