Multivariate Analysis: Canonical Discriminant Analysis

The Output Variables Tab

You can use the Output Variables tab (Figure 29.13) to add analysis variables to the data table. If you request a plot that uses one of the output variables, then that variable is automatically created even if you did not explicitly select the variable on the Output Variables tab.

The following list describes each output variable added to the data table and indicates how the output variable is named. y represents the name of the classification variable.

Posterior probabilities of group membership
adds variables named CDAProb_x, where x is the name of an X variable.
Predicted groups
adds a variable named CDAPred_y that contains the name of the group to which each observation is assigned.
Canonical scores
adds variables named CDA_1 through CDA_k, where k is the number of canonical components.

If a classification fit plot is requested on the Plots tab, then a variable named CDALogProb_y is created, as described in the section "The Plots Tab".

ugmultcdaoutputtab.png (4180 bytes)

Figure 29.13: The Output Tab


Previous Page | Next Page | Top of Page