I have searched the list archieve about how to calculate BIC for
regression model with random effects without luck. In cross-sectional
case, this can be easily done using "fitstat", but I have not found one
single post on how to do it in presence of random effects. In Skrondal and
Rabe-Hesketh's (2004, pp.264-265) new book there is some discussion on
this, but it's more like "some people did this, other people did that"
instead of "we think the best way to do this is". In other words, it is
very enlightening for further methodological research but is not extremely
helpful for a non-statistician who is working on substantive research
question. I would like to have some input from other people on the list.
For example, I have a random intercept logistic model with log-likelihood
-72717, 32 fixed effects parameter, one random effect parameters, 2059
clusters (aggregate-level units), and 530372 individuals, how to calculate
BIC using these numbers?
