PRINT Subcommand (CATREG command)

The PRINT subcommand controls the display of output. The output of the CATREG procedure is always based on the transformed variables. However, the correlations of the original predictor variables can be requested as well by the keyword OCORR. The default keywords are R, COEFF, DESCRIP, and ANOVA. That is, the four keywords are in effect when the PRINT subcommand is omitted or when the PRINT subcommand is given without any keyword. If a keyword is duplicated or it encounters a contradicting keyword, such as /PRINT = R R NONE, then the last one silently becomes effective.

  • The REGU keyword is only applicable if a REGULARIZATION method is specified.

    R. Multiple R. Includes R 2, adjusted R 2, and adjusted R 2 taking the optimal scaling into account.

    COEFF. Standardized regression coefficients (beta). This option gives three tables: a Coefficients table that includes betas, standard error of the betas, t values, and significance; a Coefficients-Optimal Scaling table, with the standard error of the betas taking the optimal scaling degrees of freedom into account; and a table with the zero-order, part, and partial correlation, Pratt's relative importance measure for the transformed predictors, and the tolerance before and after transformation. If the tolerance for a transformed predictor is lower than the default tolerance value in the Regression procedure (0.0001) but higher than 10E–12, this is reported in an annotation. If the tolerance is lower than 10E–12, then the COEFF computation for this variable is not done and this is reported in an annotation. Note that the regression model includes the intercept coefficient but that its estimate does not exist because the coefficients are standardized.

    DESCRIP(varlist). Descriptive statistics (frequencies, missing values, and mode). The variables in the varlist must be specified on the VARIABLES subcommand but need not appear on the ANALYSIS subcommand. If DESCRIP is not followed by a varlist, Descriptives tables are displayed for all of the variables in the variable list on the ANALYSIS subcommand.

    HISTORY. History of iterations. For each iteration, including the starting values for the algorithm, the multiple R and the regression error (square root of (1–multiple R 2)) are shown. The increase in multiple R is listed from the first iteration.

    ANOVA. Analysis-of-variance tables. This option includes regression and residual sums of squares, mean squares, and F. This options gives two ANOVA tables: one with degrees of freedom for the regression equal to the number of predictor variables and one with degrees of freedom for the regression taking the optimal scaling into account.

    CORR. Correlations of the transformed predictors.

    OCORR. Correlations of the original predictors.

    QUANT(varlist). Category quantifications. Any variable in the ANALYSIS subcommand may be specified in parentheses after QUANT. If QUANT is not followed by a varlist, Quantification tables are displayed for all variables in the variable list on the ANALYSIS subcommand.

    REGU. Penalty values, R-squared, and the regression coefficients for each regularized model, and, if a RESAMPLE method is specified or if supplementary objects (tests cases) are specified, the prediction error or Test MSE.

    NONE. No PRINT output is shown. This is to suppress the default PRINT output.

  • The keyword TO in a variable list can be used only with variables that are in the ANALYSIS subcommand, and TO applies only to the order of the variables in the ANALYSIS subcommand. For variables that are in the VARIABLES subcommand but not in the ANALYSIS subcommand, the keyword TO cannot be used. For example, if /VARIABLES = v1 TO v5 and /ANALYSIS is v2 v1 v4, then /PRINT QUANT(v1 TO v4) will give two quantification plots, one for v1 and one for v4. (/PRINT QUANT(v1 TO v4 v2 v3 v5) will give quantification tables for v1, v2, v3, v4, and v5.)