Hi,

I am calculating the relative variable importance value of different predictors using AIC model selection procedures. 

It seems logical that " that if I include interactions, then I can only compare the Relative Importance Weights (RIWs) of main effects with each other, and I can only compare the RIWs of interactions with each other. I cannot compare main effect RIWs with interaction RIWs (because main effects are present in more models than interactions)."

but, anyone can provide me a citation for this?

thanks

More Mario Garrido's questions See All
Similar questions and discussions