Hi, I am a set data (bird abundance) from a a complete factorial scheme with three factors (Age, Site and Management) and two treatments per factor. Each combination of the factors was replicated four times (a total of 32 stands). I am trying to use ADONIS (vegan) to check whether bird assemblages vary according to these factors. I was checking the vegan tutorial, and there is an example with a double interaction. But I can not find any case (internet) with triple interactions. I run adonis(donesp~esp$AGE*esp$SITE*esp$MANAG, permutations = 1000, method = "bray"). The results sound good, but I am not very sure whether it is right to include a third factor. Cheers Jorge -- View this message in context: http://r.789695.n4.nabble.com/ADONIS-triple-interaction-tp3698178p3698178.html Sent from the R help mailing list archive at Nabble.com.