Model Fitting: Linear Regression

You can use the Variables tab to specify the variables for the Linear Regression analysis.

The Variables tab is shown in Figure 21.6. The Y variable is the response variable. The dialog box supports multiple X (explanatory) variables. All X and Y variables must be interval variables.

The Linear Regression analysis does not support nominal classification variables, nor does it support specifying interaction effects such as X1*X2 or higher-order polynomial effects such as X1. You can create models with these features by using the Generalized Linear Models analysis, as described in Chapter 24: Model Fitting: Generalized Linear Models.