In the Fit Least Squares report, the Effect Tests option appears only when there are fixed effects in the model. The effect test for a given effect tests the null hypothesis that all parameters associated with that effect are zero. An effect might have only one parameter as for a single continuous explanatory variable. In this case, the test is equivalent to the t test for that term in the Parameter Estimates report. A nominal or ordinal effect can have several associated parameters, based on its number of levels. The effect test for such an effect tests whether all of the associated parameters are zero.
Note the following:
• Effect tests are conducted, when possible, for effects whose terms are involved in linear dependencies. See Models with Linear Dependencies among Model Terms.
• Parameterization and handling of singularities differ from the SAS GLM procedure. For more information about parameterization and handling of singularities, see “The Factor Models”.
The Effects Test report contains the following columns:
Source
The effects in the model.
Nparm
The number of parameters associated with the effect. A continuous effect has one parameter. The number of parameters for a nominal or ordinal effect is one less than its number of levels. The number of parameters for a crossed effect is the product of the number of parameters for each individual effect.
DF
The degrees of freedom for the effect test. Ordinarily, Nparm and DF are the same. They can differ if there are linear dependencies among the predictors. In such cases, DF might be less than Nparm, indicating that at least one parameter associated with the effect is not testable. Whenever DF is less than Nparm, the note LostDFs appears to the right of the line in the report. If there are degrees of freedom for error, the test is conducted. See Effect Tests Report.
Sum of Squares
The sum of squares for the hypothesis that the effect is zero.
Mean Square
(Hidden column.) The mean square for the effect, which is the sum of squares for the effect divided by its DF.
F Ratio
The F statistic for testing that the effect is zero. The F Ratio is the ratio of the mean square for the effect divided by the mean square for error. The mean square for the effect is the sum of squares for the effect divided by its degrees of freedom.
Prob > F
The p-value for the effect test.
η2 Effect Size
(Hidden column.) The η2 (eta squared) effect size index statistic for the effect. This value is calculated as the effect sum of squares divided by the total sum of squares. See Albers and Lakens (2018).
ω2 Effect Size
(Hidden column.) The ω2 (omega squared) effect size index statistic for the effect. This statistic is a less biased alternative to η2. See Albers and Lakens (2018).
Note: To make the hidden columns visible in the table, right-click in the table and select the column name from the Columns submenu.