I could really use some advice with an interaction interpretation.
I have conducted a 3 way repeated measures anova with terms A, B and C. A has 2 levels, B has 3 levels and C has 4 levels.
My results show a significant main effect of A and a significant interaction effect of BxC.
I am aware that if there is an interaction effect then one should not interpret the main effect.
Does that hold true in this situation when the variable A with a main effect does not experience any significant interactions?
Best Answer
The general advice to not interpret a main effect if there are interactions is too strong, at the very least. For example, if the variable of interest necessarily has a limited range of values (e.g. sex), and there is a strong main effect, then it's perfectly reasonable to interpret the main effect even if there is also an interaction.
Regardless, the advice only applies to the variables for which there are interactions. So, in your case interpret your A main effect and your B x C interaction separately.