[R-sig-ME] Extracting Standard Errors of Uncorrelated Random Effects?

[Derek Dunfield]

Hello all:
I was hoping to extract SE for my random effects to get a better idea
of their precision for each grouping factor.

Andrew Gelman has developed a nice package called "Arm" which does
this seamlessly for models with correlated random effects such as
Reaction ~ 1 + Days + (1 + Days | Subject)

When I try to run this on an uncorrelated model such as
Reaction ~ 1 + Days + (1 | Subject) + (0 + Days | Subject)

I get the error "Error in .local(object, ...) : Code not written yet"

I believe this may be due to some unfinished code in the lme4 package
for ranef, though I'm not sure.

Does anyone have an idea how I could go about calculating these standard errors?

Many thanks in advance for you help!
:Derek

--
Derek Dunfield, PhD
Postdoctoral Fellow, MIT Intelligence Initiative
Sloan School of Management
MIT Center for Neuroeconomics, Prelec Lab
77 Massachusetts Ave E62-585
Cambridge MA 02139