Testing the joint significance of multiple coefficients in a model

If a group of coefficients contains statistically insignificant coefficients, a combined test can determine whether the group considered as a whole is statistically significant or not. Sometimes a group of coefficients may be insignificant when considered individually, but significant when considered as a group.

To test the combined significance of two or more model coefficients:

  1. In the Model view, select two or more coefficients in the explanatory variables table (Command-click or Shift-click to select multiple rows)
  2. Below the coefficient picture view, choose Coefficients are zero from the button labeled Null hypothesis
  3. The result of the combined significance test will appear in the coefficient picture view

To test the combined signficance of the model as a whole, simply select all coefficients.

Wizard performs joint significance tests using the Wald test. An F statistic is constructed for linear models, and a chi-squared statistic is constructed for non-linear models. Likelihood ratio and score tests are not available.

Other kinds of hypotheses can be tested in a similar manner by choosing a different null hypothesis.

See also:


Back to Wizard Help