The TRANSREG Procedure
- Overview
-
Getting Started
-
Syntax
-
Details
Model Statement Usage Box-Cox Transformations Using Splines and Knots Scoring Spline Variables Linear and Nonlinear Regression Functions Simultaneously Fitting Two Regression Functions Penalized B-Splines Smoothing Splines Smoothing Splines Changes and Enhancements Iteration History Changes and Enhancements ANOVA Codings Missing Values Missing Values, UNTIE, and Hypothesis Tests Controlling the Number of Iterations Using the REITERATE Algorithm Option Avoiding Constant Transformations Constant Variables Character OPSCORE Variables Convergence and Degeneracies Implicit and Explicit Intercepts Passive Observations Point Models Redundancy Analysis Optimal Scaling OPSCORE, MONOTONE, UNTIE, and LINEAR Transformations SPLINE and MSPLINE Transformations Specifying the Number of Knots SPLINE, BSPLINE, and PSPLINE Comparisons Hypothesis Tests Output Data Set OUTTEST= Output Data Set Computational Resources Unbalanced ANOVA without CLASS Variables Hypothesis Tests for Simple Univariate Models Hypothesis Tests with Monotonicity Constraints Hypothesis Tests with Dependent Variable Transformations Hypothesis Tests with One-Way ANOVA Using the DESIGN Output Option Discrete Choice Experiments: DESIGN, NORESTORE, NOZERO Centering Displayed Output ODS Table Names ODS Graphics
-
Examples
- References
| Avoiding Constant Transformations |
There are times when the optimal scaling produces a constant transformed variable. This can happen with the MONOTONE, UNTIE, and MSPLINE transformations when the target is negatively correlated with the original input variable. It can happen with all transformations when the target is uncorrelated with the original input variable. When this happens, the procedure modifies the target to avoid a constant transformation. This strategy avoids certain nonoptimal solutions.
If the transformation is monotonic and a constant transformed variable results, the procedure multiplies the target by –1 and tries the optimal scaling again. If the transformation is not monotonic or if the multiplication by –1 did not help, the procedure tries using a random target. If the transformation is still constant, the previous nonconstant transformation is retained. When a constant transformation is avoided by any strategy, this message is displayed: "A constant transformation was avoided for name."
With extreme collinearity, small amounts of rounding error might interact with the instability of the coefficients to produce target vectors that are not positively correlated with the original scaling. If a regression coefficient for a variable is zero, the formula for the target for that variable contains a zero divide. In a multiple regression model, after many iterations, one independent variable can be scaled the same way as the current scaling of the dependent variable, so the other independent variables have coefficients of zero. When the constant transformation warning appears, you should interpret your results with extreme caution, and recheck your model.