This section applies to actions in the following action sets: gam, phreg, pls, quantreg, and regression.
Partitioning parameters specify how observations in the input data set are logically partitioned into disjoint subsets for model training, validation, and testing. For more information, see the section Using Validation and Test Data. Either you can designate a variable in the input data table and a set of formatted values of that variable to determine the role of each observation, or you can specify proportions to use for randomly assigning observations to each role.
Specifying the partByFrac parameter enables you to specify the proportion of observations used for testing and validation with the test and validate subparameters. The remaining fraction of the observations are assigned to the training role. You can specify the seed used for the random number generator by using the seed subparameter; by default, the seed is generated by reading the time of day from the computer’s clock.
Specifying the partByVar parameter enables you to specify a variable containing the roles of the observations; this variable cannot also appear as an analysis variable. The test, train, and validate subparameters specify the formatted values of this variable that are used to assign observation roles. If you do not specify the train subparameter, then all observations whose role is not determined by the test or validate subparameters are assigned to the training role.
For more information about these parameters, see the Syntax section of the specific action chapters.