Please forgive the very basic maths question! I have a gamma model with log link. I’m not sure what to do with the results.
For example, another model is a categorical model with logic link, so I exp(model)
to get log odds, which I can easily interpret and understand. I’m not sure what to do with my gamma and log outcome though? Would I do 1/model
?
The model looks something like:
modeltest <- brm(
formula = score ~ 1 + group,
data = df,
family = Gamma(link = "log"), seed = 64,chains = 5, control = list(adapt_delta = 0.99),
iter = 10000,
cores = 5
)
Thanks very much!