I am fitting a glmm for count data as follow:
glmmTMB(counts ~ treatmens + vegetation + days + (1 + treatments|sites), data = data, family = nbinom1, ziformula = ~1))
As far as I understand the glmmTMB manual this means that I think that the effect of treatments varies across sites, and that the zero-inflation is assumed to be constant across data. However, I would like to model it in a way that the zero-inflation will vary by sites. Now I am a bit confused on how to specify this in the model, something like:
ziformula = ~sites or
ziformula = ~(1|sites).
It is a bit hard for me to grasp the differences