glmer question

I would like to fit the following model:

logit(p_{ij}) = \mu + a_i + b_j

where    a_i ~ N(0, \sigma_a^2) ,   b_j ~ N(0, \sigma_b^2)   and   \sigma_a
= \sigma_b.

Is it possible to fit a model with such a constraint on the variance
components in glmer?

--
View this message in context: http://r.789695.n4.nabble.com/glmer-question-tp4351829p4351829.html
Sent from the R help mailing list archive at Nabble.com.