Setting Options

Option	Description
Methods
Method	specifies the general factor extraction method to use. You can choose from these methods: Partial least squares regression De Jong’s SIMPLS Principal components regression Reduced rank regression
Center the responses and predictors	includes the intercept in the model. By default, the responses and predictors are centered, and the intercept is not included in the model.
Specify the number of factors	specifies the number of factors to extract. The default is . p is the number of predictors (or the number of dependent variables when you select Reduced rank regression as the method). N is the number of runs (observations).
Cross Validation
Cross validation method	specifies the cross validation method. By default, no cross validation method is selected. Here are the available methods: Exclude one observation at a time Exclude every nth observation Exclude blocks of consecutive observations Exclude observations at random
Details
Algorithm	specifies the algorithm to use to compute the extracted factors. You can choose from these algorithms: Iterative NIPALS requests the usual iterative NIPALS algorithm. Singular value decomposition bases the extraction on the singular value decomposition of X′Y. Eigenvalue decomposition bases the extraction on the eigenvalue decomposition of Y′XX′Y. Iterative RLGW is an iterative approach that is efficient when there are many predictors.
Specify the maximum number of iterations	specifies the maximum number of iterations if you selected the Iterative NIPALS or Iterative RLGW algorithm.
Statistics
You can choose to include the default statistics in the results, or you can choose to include these additional statistics: Coefficients of final predictive model, which lists the coefficients of the final predictive model for the responses. The coefficients for predicting the centered and scaled responses based on the centered and scaled predictors are displayed. The coefficients for predicting the raw responses based on the raw predictors are also displayed. Variation accounted for in responses and predictors. This option lists the amount of variance accounted for in each response and predictor. The option also includes the average response and predictor sum of squares accounted for by each successive factor. Details of the fitted model, which is the details of the fitted model for each successive factor. The details listed are different for different extraction methods.
Plots
Select the plots to include in the output. By default, only the correlation loading plot is included in the output. You can choose to include these additional plots: correlation loading plot diagnostics plots residuals of dependent by independent variables profiles of regression coefficients Note: This plot is available only when you create two or more effects on the Models tab. variable importance factors distance plots for X and Y models matrix of X-scores against Y-scores