Dear Pedro, How to test for an interaction--or, even, how to pose the question of an interaction--in randomization-based inference is not at all obvious. And, in the permutation test context reliance has been placed on the exchangeability of (estimated) residuals under an additive, homoscedastic model. Where estimated, the residuals are not exactly exchangeable. A reference you might find useful is Pesarin, F (2001) "Multivariate permutations tests." Wiley: Chichester, UK. His method of synchronized permutations "may" be applied to test for interactions under some limited circumstances. Pedro de Barros writes, in part: Dear All, I am trying to build a randomization test for interaction The problem is as follows: I have a set of stations where the occurrence and biomass of each species being investigated was recorded. <snip> I would really appreciate any pointer to a solution of this problem. I believe it is not complicated (and probably quite obvious) but the solution keeps out of reach, even though I have been searching for over a week. Thanks, Pedro ********************************************************** Cliff Lunneborg, Professor Emeritus, Statistics & Psychology, University of Washington, Seattle cliff at ms.washington.edu