Data can be partitioned into sets before modeling to avoid overfitting and to select a good predictive model. This process uses part of the original data to estimate parameters and uses the rest of the data to tune or evaluate the parameters, or do both. In JMP Pro, you can partition the data into two or three sets in the following ways:
Train and Evaluate
Partitions the data into two sets, called Training and Validation. The training set is used to estimate the model parameters. The validation set is used to independently evaluate the performance of the fitted model.
Train and Tune
Partitions the data into two sets, called Training and Validation. The training set is used to estimate the model parameters. The validation set is used in the model fitting algorithm to tune the model parameters and ultimately choose a model with good predictive ability. There is no independent model evaluation done in this case.
Train, Tune, and Evaluate
Partitions the data into three sets, called Training, Validation, and Test. The training set is used to estimate the model parameters. The validation set is used in the model fitting algorithm to tune the model parameters and ultimately choose a model with good predictive ability. The test set is then used to independently evaluate the performance of the fitted model.