[R-sig-ME] Interpreting the output of summary() of a glmer-object

[Ben Bolker]

Hans Ekbrand <hans at ...> writes:

> 
> On Tue, Sep 25, 2012 at 02:04:19AM +0000, Ben Bolker wrote:
> > Hans Ekbrand <hans at ...> writes:
> > 

[snip]

> > > 
> > > load(url("http://sociologi.cjb.net/temp/a.strange.df.RData"))
> > > my.fit.1 <- glmer(MV744A ~ (1|MV024), 
> > >    data = a.strange.df, family = "binomial")
> > > summary(my.fit.1)
> > > 

[snip]

> > > Random effects:
> > >  Groups Name        Variance Std.Dev.
> > >  MV024  (Intercept) 0.40558  0.63685 
> > > Number of obs: 73601, groups: MV024, 29
> > > 

[snip]

> 
> So, if I understand you - which I think I do - then 0.63685 is 
> simply the standard deviation of ranef(my.fit.1)?
> 
> When I try to compute that manually I get a numerically 
> close figure, but not quite the same:
> 
> sd(unlist(ranef(my.fit.1)))
> [1] 0.6423346
> 
> I am on the right track?
> 

  I think this has been discussed previously on the list (although
I can't point you to a precise spot), but: 

http://permalink.gmane.org/gmane.comp.lang.r.lme4.devel/8580

says

"Generally you will find that the variance of the values returned by
ranef is less than the estimated variance because of shrinkage."

  Sorry I can't go into  more detail right now.