R help - Jul 2006 - analogue of group option of SAS MIXED/random in R

Dear list,

I am trying to use lme to build the analogue of the following SAS MIXED
random specification:

random int+Variable1+Variable2 /subject = Subject group=Condition type=vc;

which gives a Condition-blocked heterogeneity in the random effects
variance-covariance matrix.

Needless to say, I have a hard time in specifying Condition-specific
heterogeneities in the variance-covariance parameters.

I initially tried the following commands (without Condition-heterogeneity in
the random effects):

G.Data<-groupedData(Response~1|Subject,data=In.Data)
Fit1<-lme(Response~1+Variable1+Variable2*Condition,random=pdDiag(~1+Variable1+Variable2),method="REML",data=G.Data)

but have no idea about where to go from here (note that I don't want to nest
Subject in Condition).

Thanks!!

    Bruno

Well,
just in case somebody is interested, the following R code gives the same
estimates as the SAS code below:

######R code###########
G.Data<-groupedData(Response~1|Subject,data=In.Data)
G.Data$Condition<-as.ordered(G.Data$Condition)
G.Data$Const<-rep(1,length(Variable1))
tmp<-pdDiag(~Condition:Const+Condition:Variable1+Condition:Variable2-1)
Fit1<-lme(Response~1+Variable1+Variable2*Condition,
random=tmp,
method="REML",data=G.Data)


########SAS code########
proc mixed data=InData;class Subject Condition;
model Response=Variable1 Variable2 Condition Variable2*Condition;
random int Variable1 Variable2/subject = Subject group=Condition type=vc;
run;



    Bruno



----- Original Message ----- 
From: "Bruno L. Giordano" <bruno.giordano at music.mcgill.ca>
To: <r-help at stat.math.ethz.ch>
Sent: Monday, July 03, 2006 5:56 PM
Subject: [R] analogue of group option of SAS MIXED/random in R

> Dear list,
>
> I am trying to use lme to build the analogue of the following SAS MIXED
> random specification:
>
> random int+Variable1+Variable2 /subject = Subject group=Condition type=vc;
>
> which gives a Condition-blocked heterogeneity in the random effects
> variance-covariance matrix.
>
> Needless to say, I have a hard time in specifying Condition-specific
> heterogeneities in the variance-covariance parameters.
>
> I initially tried the following commands (without Condition-heterogeneity
> in
> the random effects):
>
> G.Data<-groupedData(Response~1|Subject,data=In.Data)
>
Fit1<-lme(Response~1+Variable1+Variable2*Condition,random=pdDiag(~1+Variable1+Variable2),method="REML",data=G.Data)
>
> but have no idea about where to go from here (note that I don't want to
> nest
> Subject in Condition).
>
> Thanks!!
>
>    Bruno
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html
>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Bruno L. Giordano, PhD
CIRMMT
Schulich School of Music, McGill University
555 Sherbrooke Street West
Montr?al, QC H3A 1E3
Canada
http://www.music.mcgill.ca/~bruno/