Displaying 1 result from an estimated 1 matches for "taxon1".
Did you mean:
taxon
2009 Nov 02
1
Interaction contrasts or posthoc test for glm (MASS) with ANOVA design
...Site:Taxon interaction is significant, I need to do the equivalent
to a "post-hoc test" for ANOVA, however, the same tests (e.g. Tukey HSD) do
not seem to be applicable for the GLM. I tried specifying orthogonal
contrasts, but could not figure out what the interaction contrast (see
Site1:Taxon1 in below example) means.
Could you please advise me how to specify a meaningful interaction contrast
(i.e. contrast species within sites)? Alternatively, could you recommend a
way to do posthoc comparisons?
Thanks for your time and kind regards
Maya
> library(MASS)
> counts <- c(1, 4, 9...