Hi, I am trying to fit a ANCOVA model using lmRob. The P-values of the variables in the model differ hugely between the summary() function and the anova() function (from >0.8 in the summary to <0.001in the anova for the same variable). I understand that with an ANCOVA the order in which the variables are added to the model matters and that this influences the P-value, but can this make such a big difference? Which P-values are best to use? Also, could this be an indication something is wrong with my model? Any help would be greatly appreciated! Thanks, Geertje ~~~~ Geertje van der Heijden PhD student Tropical Ecology School of Geography University of Leeds Leeds LS2 9JT Tel: (+44)(0)113 3433345 Email: g.m.f.vanderheijden04@leeds.ac.uk [[alternative HTML version deleted]]