Contrasts for Between-Group Factors / Contrasts for Within-Subject Factors

Click the Contrasts for LS means button on the GLM, GRM, and ANOVA Results - Comps tab (or the Specify contrasts for LS means button on the GLM, GRM, and ANOVA More Results - Planned Comps tab) to display either the Contrasts for Between-Group Factors dialog or the Contrasts for Within-Subject Factors dialog.

If you have selected the Together (contrast vectors) option button in the Enter contrasts separately or together group box and have selected an interaction involving two or more between effects in the Effect drop-down box, the Contrasts for Between-Group Factors dialog is displayed. If you have selected the Together (contrast vectors) option button in the Enter contrasts separately or together group box and have selected an interaction involving two or more within-subjects (repeated measures) effects in the Effect drop-down box, the Contrasts for Within-Subject Factors dialog is displayed.

CONTRASTS

Enter the desired contrast coefficients for the respective combination of treatment levels (cells of the between-group or within-subject design) in the CONTRASTS specification column(s). To learn more about the logic and interpretation of contrast analysis refer to the ANOVA/MANOVA module Overview section; examples of how to specify contrasts are also discussed in that module, in the Notes section, for between-group designs as well as repeated measures designs.

The general rules for generating contrast coefficients are as follows.

(1) The contrast must have as many coefficients as there are combined number of levels (cells in the effect).

(2) Cells that are to be omitted in the contrast are assigned a 0 (zero).

(3) Cells that are to be compared against each other are assigned positive or negative integer values; however, it is important that the sum of such contrasts is equal to zero.

(4) Levels that are to be collapsed are assigned identical integer values (e.g., all 1's).

If there are missing cells in the between-group design then asterisks are shown next to the respective rows. Only 0's may be entered for those cells.

OK. Click the OK button to close the dialog and return to the GLM, GRM, and ANOVA Results - Comps tab, after you are satisfied with the current contrast coefficients.

Cancel

Click the Cancel button to close the dialog and return to the GLM, GRM, and ANOVA Results - Comps tab, ignoring any changes you have made.

Delete column

Click the Delete column button to delete the entire selected column.

Insert Value

The Insert Value group box allows you to quickly enter contrast coefficients. Select the Cell option button and click one of the number buttons to replace the coefficient in the cell for the selected variable with that number (i.e., only that cell will be replaced). Select the Row option button and click one of the number buttons to replace all of the coefficients for a variable with the selected number (i.e., the entire row of contrast coefficients will be replaced with this number). Finally, select the Column option button and click one of the number buttons to replace the coefficients for all of the variables with the selected number (i.e., the entire column of contrast coefficients will be replaced with this number).

<<

Click the << button to display the previous CONTRASTS column. Note that this option will only be available when applicable.

>>

Click the >> button to display the next CONTRASTS column. Please note that this option will only be available when applicable.

See also GLM - Index.