Comparisonsoverview how to example data see also
ComparisonsStat > ANOVA > General Linear Model > Comparisons
Use a general linear model to examine which factor level means are significantly different and to estimate by how much they are different. Specify the terms to compare, as well as the type of multiple comparisons. Choose the comparison procedure based on the means that you want to compare and the type of confidence level that you want to specify.
Read Multiple comparisons of means to learn how to choose among the options. See Stored Model Overview for a discussion about how to use stored models.
|
Note |
If your model includes nested factors or random factors, or if it uses binary coding, there are restrictions on the procedures that you can perform. See Restrictions for General Linear Models for details. |
Response: Choose a response variable from the drop-down list.
Type of comparison:
Pairwise: Choose when you want to compare all combinations of means for the terms that you select.
With a control: Choose to compare treatment means to the mean of a control group. When this method is suitable, it is inefficient to use pairwise comparisons because the confidence intervals are wider and the hypothesis tests are less powerful for a given simultaneous confidence level.
Method: Check the multiple comparison method that you want to use.
Tukey: Check to compare all pairs of groups, while controlling the simultaneous confidence level. For all-pairwise comparisons, Tukey's method is generally more powerful than the Bonferroni and Sidak methods.
Fisher: Check to compare groups while controlling the individual confidence level. Fisher's is less common because it does not control the simultaneous confidence level, which often decreases to an unacceptable level.
Dunnett: Check to compare treatment means to the mean of a control group, while controlling the simultaneous confidence level. For comparisons with a control, Dunnett's method is generally more powerful than the Bonferroni and Sidak methods.
Bonferroni: Check to compare groups while controlling the simultaneous confidence level.
Sidak: Check to compare groups while controlling the simultaneous confidence level.
Terms for comparisons: Select the terms that you want to compare and click C = Compare levels for this item. Or, double-click the terms that you want to compare.
Control levels: If you chose With a control, you must choose a control level for each factor that you select.