SAVE Subcommand (GENLINMIXED command)

The SAVE subcommand writes optional temporary fields to the active dataset.

PREDICTED_VALUES(varname). Predicted value of the target. The default field name is PredictedValue.

PREDICTED_PROBABILITY(rootname). Predicted probabilities of the target. If the target is categorical, this keyword saves the predicted probabilities of the first n categories. The values are cumulative probabilities for ordinal targets. The value of n is specified by the MAX_CATEGORIES keyword.

• Specify a unique, valid variable name. The default root name is PredictedProbability.
• If the dependent variable is continuous, this keyword is ignored with a warning.

MAX_CATEGORIES. The maximum number of categories for which predicted probabilities and confidence intervals (for a categorical target) should be saved.

• Specify a positive integer. The default is 25.
• This keyword is ignored if predicted probabilities or confidence intervals (for a categorical target) are not saved.

CONFIDENCE(varname). Confidence in predicted value for categorical target. The computed confidence can be based on the probability of the predicted value (the highest predicted probability) or the difference between the highest predicted probability and the second highest predicted probability. The default field name is Confidence.

CONFIDENCE_METHOD. Method for computing confidence. The computed confidence can be based on the probability of the predicted value (the highest predicted probability) or the difference between the highest predicted probability and the second highest predicted probability.

CONFIDENCE_INTERVALS(rootname). Upper and lower confidence intervals. For all distributions except the multinomial, this creates two variables and the default root name is CI, with _Lower and _Upper as the suffixes. Specify a root name in parentheses to override the default.

For the multinomial distribution and a nominal target, one field is created for each dependent variable category. CONFIDENCE_INTERVALS saves the lower and upper bounds of the predicted probability for the first 25 categories by default. The default root name is CI, and the default field names are CI_Lower_1, CI_Upper_1, CI_Lower_2, CI_Upper_2, and so on, corresponding to the order of the target categories. Specify a root name in parentheses to override the default. The value of n is specified by the MAX_CATEGORIES keyword.

For the multinomial distribution and an ordinal target, one field is created for each dependent variable category except the last (see the TARGET_SORT_ORDER keyword). CONFIDENCE_INTERVALS saves the lower and upper bounds of the cumulative predicted probability for the first 25 categories, up to but not including the last, by default. The default root name is CI, and the default field names are CI_Lower_1, CI_Upper_1, CI_Lower_2, CI_Upper_2, and so on, corresponding to the order of the target categories. Specify a root name in parentheses to override the default. The value of n is specified by the MAX_CATEGORIES keyword.

PEARSON_RESIDUALS(varname). Pearson residuals. The default field name is PearsonResidual.