parameters
parameters copied to clipboard
Analog to `coef()` for mixed effects models
It would be nice to have an analog to coef()
for mixed effects models. This returns fixef() + ranef()
for each random parameter. Modeling packages vary in whether SEs and intervals are provided for these results (e.g., brms does, glmmTMB hopes to, lme4 won't).
We could return those probably using the effects
and component
arguments, what would you suggest?
I think effects = "group_specific"
would be good.
"group_level" ?
"Level" usually means the specific levels of the group factor though, and there's some confusion with the group_level
argument. See also this response https://twitter.com/smartin2018/status/1390738366056960003?s=21