I built a glmmTMB model using a gamma distribution as my data look like a poisson distribution but with continuous variable. My model looks like this:
RB.ng.CO2_C.gsol.h ~ treatment * tree.specie + (1|bloc)
The treatment factor has 8 levels and the tree.specie factor has 6 levels.
I want to perform a Dunnett post-hoc test with this model to extract the significant difference between my results.
I have tried to do it using the emmeans package, but I got an error saying that glmmTMB cannot be handled.
emm <- emmeans(m1, ~ treatment * tree.specie, data = RBA2022)
Error in (function (object, at, cov.reduce = mean, cov.keep = get_emm_option("cov.keep"), : Can't handle an object of class “glmmTMB” Use help("models", package = "emmeans") for information on supported models.
Do you have any idea of how to do that post-hoc test?