Parameters | Pattern Discovery | PROC PLS Options

Enter SAS PROC PLS options in this field to override default parameters for calculating the principal components.

• Option is the PROC PLS option,

•

This option specifies the cross validation method to be used. The method CV=ONE requests one-at-a-time cross validation.Note: By default, no cross validation is performed. This option specifies that van der Voet’s randomization-based model comparison test^{1}be performed to test models with different numbers of extracted factors against the model that minimizes the predicted residual sum of squares.

• PVAL=n specifies the cutoff probability for declaring an insignificant difference. The default value is 0.10.

• STAT=test-statistic specifies the test statistic for the model comparison. You can specify either T2, for Hotelling’s T2 statistic, or PRESS, for the predicted residual sum of squares. The default value is T2.

• NSAMP=n specifies the number of randomizations to perform. The default value is 1000.

• SEED=n specifies the seed value for randomization generation (the clock time is used by default). This option specifies that continuous model variables be centered and scaled before centering and scaling the model effects in which they are involved. The rescaling specified by the VARSCALE option is sometimes more appropriate if the model involves crossproducts between model variables. However, the VARSCALE option still might not produce the model that you expect.

van der Voet, H. (1994) Comparing the predictive accuracy of models using a simple randomization test. Chemometric and Intelligent Laboratory Systems 25: 313–323

Type specific PROC PLS options in the PROC PLS Options field.Refer to the PROC PLS documentation for more information.