Specifying model terms for ordinal logistic regression

In the Model text box, enter the terms you want to include in the model. The model can include continuous and categorical variables. You can include crossed or nested terms.

To specify the model terms, use the following rules:
  • Use * to specify an interaction term. For example, A*B is the interaction of factors A and B.
  • Use ( ) to indicate nesting. When B is nested within A, type B(A). When C is nested within both A and B, type C(A B). Terms in parentheses are always factors in the model and are listed with blank spaces between them. To preserve hierarchy, the model also needs the interactions between terms in parentheses.
  • Use | or ! to indicate that you want to include all variables and their interaction terms in the model. For example, A | B | C will include A, B, C, A*B, A*C, B*C, A*B*C in the model.
  • Use – to remove terms from the model. For example, A | B | C – A*B*C includes all variables and their interactions except for A*B*C.
  • Models must be hierarchical. In a hierarchical model, if a higher-order term is included, all lower order interactions and main effects that comprise the higher-order term appear in the model. For example, a model that includes the interaction term A*B*C is hierarchical if the model includes the following terms: A, B, C, A*B, A*C, and B*C. Alternatively, A|B|C - A*B is not hierarchical.
Here are some examples of what to type in the Model text box:
  • Two variables crossed: A B A*B
  • Three variables crossed: A B C A*B A*C B*C A*B*C
  • Crossed and nested (B nested within A, and both crossed with C): A B(A) C A*C C*B(A)

    When a term contains both crossed and nested terms, put the crossed variable first, as in C*B(A), not B(A)*C.

  • Crossed and nested terms using | : A B(A) C A*C B*C is equal to A | B (A) | C

When you specify the model terms and the column names contain spaces or special symbols, enclose the column name in single quotes. For example, if the columns names are Brown sugar and White sugar, specify the terms as follows: 'Brown sugar' 'White Sugar' 'Brown sugar' * 'White Sugar'.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy