[R-sig-ME] anova on lmer object

[Marianne Promberger]

Doug Adams <fog0 at gmx.com> 09-Feb-10 07:21:
> When you use anova() on an lmer object -- like " anova(lmer(...)) "
> -- what is being calculated?  I assume it's a test for the
> significance of fixed effects, but just wanted to know how it's
> being done.  :)

It is a likelihood ratio test. 

I'm also just getting my head around mixed models and lmer() and found
this paper very helpful:

Baayen, R. H., Davidson, D. J., and Bates, D. M. (2008). Mixed-effects
modeling with crossed random effects for subjects and items. Journal
of Memory and Language, 59(4):390-412.

http://dx.doi.org/10.1016/j.jml.2007.12.005

See p 395 for comparing two models with anova()

Marianne

-- 
Marianne Promberger PhD, King's College London
http://promberger.info
R version 2.10.1 (2009-12-14)
Ubuntu 9.04