[R-sig-ME] blockdiagonal variance re in lmer

[vito muggeo]

Hi all,
I am interested in usign lmer/lmer2 to fit (G)LMM where the variance of 
the random effects is blockdiagonal or simply multiple of identity. Namely:

G=blockdiag(s1*I_1,...,s_kI_k)
G=s*I

In the lme() from the nlme package I can use the random argument

#multiple of the identity:
lme(..,random=list(id=pdIdent(~Z-1)))

#blockdiagonal
lme(..,random=list(id=pdBlocked(list(pdIdent(~Z1-1),pdIdent(~Z2-1))))
or even
random=list(id=pdIdent(~Z1-1),id=pdIdent(~Z2-1))

I cannot figure out how I can attain the same with lmer/lmer2..
Please, could anyone help me?

many thanks,
vito


-- 
====================================
Vito M.R. Muggeo
Dip.to Sc Statist e Matem `Vianelli'
Università di Palermo
viale delle Scienze, edificio 13
90128 Palermo - ITALY
tel: 091 6626240
fax: 091 485726/485612