Skip to content
Prev 7781 / 20628 Next

Wald tests GLMM with glmer

Dear Thomas,

There are others on this list who are more knowledgeable than me, but I can suggest a couple things:
With the new lme4, try:
? bootMer
Five levels is not enough. In most instances, I think, you need at least 20, and ideally more than that. Though it depends on the context, and to some extent who you ask.
Could you turn this random classification into a series of fixed effects, using dummy variables?

Hope that's useful.
- Malcolm
Message-ID: <3CC49BDD-F0B9-44EF-9C34-81364164404A@bristol.ac.uk>
In-Reply-To: <mailman.4085.1332195502.4502.r-sig-mixed-models@r-project.org>