I'm following an SPSS guide online, and the procedure is to first test for a three-way interaction. In my case there was no sig. three-way interaction. Then the procedure asks me to consider two-way interactions. However, the guide says if I do not have any sig. two-way interactions, then I can stop the analysis there. Why? How come I don't consider the main effects of each factor individually? In a two-way ANOVA, you consider both the interactions and the main effects.