Prediction in PLS regression

You can use prediction in PLS for two primary purposes.
Testing prediction quality
Apply the PLS model to a test data set that includes responses for each observation but is independent from the one used to estimate the PLS model. Enter the columns of the test data set in the Prediction sub-dialog box. Minitab calculates new response values for each observation in the test data set and compares the predicted response to the actual response. Based on the comparison, Minitab provides a test R2, which indicates the model's ability to predict new responses.
Predicting new responses
Use the PLS model to estimate new response values for a set of predictors for which you have no response data. Without response data, Minitab cannot calculate a test R2.