Building a Model

Understanding Effects for Generalized Linear Models

Requirements for Building a Model

Single Effects

Create a Main Effect

Create Crossed Effects (Interactions)

Create a Nested Effect

Standard Models

Create a Full Factorial Model

Create an N-Way Factorial

Create Polynomial Effects of the Nth Order

Understanding Effects for Generalized Linear Models

For all distribution types, you can create model effects. However, if you select Zero-inflated negative binomial or Zero-inflated Poisson as the distribution on the Data tab, you can also create zero-inflated effects.

Here is an example of the contents of the Model tab if you are using a zero-inflated distribution.

Model Tab in Generalized Linear Model Task

For model effects, the intercept is included by default. To add additional model effects, click Edit Icon

to open the Model Effects Builder.

To add a zero-inflated effect, click Edit Icon

to open the Zero-Inflated Effects Builder. After you create the effect and close the Zero-Inflated Effects Builder, specify the link function for the zero-inflated model.

Requirements for Building a Model

By default, no effects are specified, which results in the task fitting an intercept-only model. Here is what you see on the Model tab.

Model Tab with Only the Intercept as an Effect

To specify a model effect, you must assign at least one variable to the Classification variables role or the Continuous variables role. On the Model tab, click Edit Icon

to open the Model Effects Builder.

When you close the Model Effects Builder, any effects that you created appear on the Model tab.

Model Tab with Intercept and Team as an Effect

Single Effects

Create a Main Effect

Select the variable name in the Variables box.
Click Add to add the variable to the list of model effects.

Create Crossed Effects (Interactions)

Select two or more variables in the Variables box. To select more than one variable, press Ctrl.
Click Cross.

Create a Nested Effect

Nested effects are specified by following a main effect or crossed effect with a classification variable or list of classification variables enclosed in parentheses. Here are examples of nested effects: B(A), C(B*A), D*E(C*B*A). In this example, B(A) is read "B within A."

Select the classification variable in the Model Effects Builder.
Click Nest. The Nested window appears.
Select the variable to use in the nested effect. Click Outer or Nested within Outer to specify how to create the nested effect.

Note: The Nested within Outer button is available only when a classification variable is selected.
Select the effect that you want to nest.
Click Add.

Standard Models

Create a Full Factorial Model

Select two or more variables in the Variables box.
Click Full Factorial.

For example, if you select the Height, Weight, and Age variables and then click Full Factorial, these model effects are created: Age, Height, Weight, Age*Height, Age*Weight, Height*Weight, and Age*Height*Weight.

Create an N-Way Factorial

Select two or more variables in the Variables box.
Click N-way Factorial and specify the value of N.

For example, if you select the Height, Weight, and Age variables, click N-way Factorial, and then specify the value of N as 2, these model effects are created: Age, Height, Weight, Age*Height, Age*Weight, and Height*Weight. If N is set to a value greater than the number of variables in the model, N is effectively set to the number of variables.

Create Polynomial Effects of the Nth Order

Select one or more continuous variables in the Variables box.
In the list of standard models, click Polynomial Order=N.
Specify higher-degree crossings by adjusting the number in the N field.

For example, if you select the Age and Height variables, click Polynomial Order=N, and specify 3 as the value of N, these model effects are created: Age, Age*Age, Age*Age*Age, Height, Height*Height, and Height*Height*Height.