I'm applying growth curve modelling and am interested in modelling a three-way interaction between predictors A x B x C. From what I remember a condition for modelling three-way interactions in regression analyses is to model all underlying related interactions as well (so AxB, AxC, and BxC in order to be allowed to model AxBxC). Can anyone confirm this (preferably providing a source) or am I confusing things and I could happily model higher-order interactions without including those lower order interactions of less interest?
$\begingroup$
$\endgroup$
1
-
$\begingroup$ I have voted to close this as duplicate. I added a comment on the other answer that the same logic applies to higher order interactions. $\endgroup$– Peter FlomOct 18, 2019 at 13:01
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
1
The short answer is yes there are very good reasons to include lower order interactions. This has been answered before:
Do all interactions terms need their individual terms in regression model?
Can we skip the lower order terms in interactions?
You might find this article helpful as well.
-
2$\begingroup$ Maybe you can add some information apart from the articles or you can sum them up. $\endgroup$– FerdiJun 5, 2017 at 15:47