Tobias Guennel
2006-Jun-19 20:06 UTC
[R] Nested variance-covariance matrix in Multilevel model
Dear R community,
I have trouble implementing a nested variance-covariance matrix in the
lme function.
The model has two fixed effects called End and logpgc, the response
variable is the logarithm to base 2 of Intensity ( log2(Intensity) )
and the random effects are called Probe and ProbeNo.
The model has the following nesting structure: A Pixel is nested within
the ProbeNo,the ProbeNo is within the ProbeEnd ( there are two ends for
every probe), and the ProbeEnd is within the Probe.
Now the problem I have is that the variance-covariance structure of the
model is quite complex and I can not find the right syntax for fitting
it in the lme function.
The variance-covariance structure is a block diagonal matrix of the form,
V1 0 0
V= 0 V2 0
0 0 V3
where V1...V3 are of the structure:
v11 v12
V1= and so on.
v21 v22
V1...V3 are assumed to have a compound symmetric variance-covariance
structure and therefore the submatrices are of the form:
Lambda Delta1 Delta1 ... Delta1
Delta1 Lambda Delta1 ... Delta1
v11=v22= .......
Delta1 ..... Lambda
Delta2 Delta2 Delta2 ... Delta2
Delta2 Delta2 Delta2 ... Delta2
v12=v21= .......
Delta2 ..... Delta2
The elements of these submatrices depend only upon the three covariance
parameters: the compound symmetry parameter delta; the variance of
random effect sigma^2g; and the residual variance sigma^2. I have
formulas for the submatrices Lambda,Delta1 and Delta2 which I can't
really paste in here.
The SAS code dealing with this model is the following:
proc mixed data=rnadeg.pnau;
title 'CV structure for PNAU';
class probepos probeno end probe pixelid newprobeid;
model logPM=end logpgc / ddfm=satterth;
random probeno newprobeid / subject=probe type=cs;
lsmeans end / diff cl; run;
Any ideas are appreciated a lot since I am kind of stuck at this point.
Thank you
Tobias Guennel
Tobias Guennel
2006-Jun-19 20:43 UTC
[R] Nested variance-covariance matrix in Multilevel model
I completely forgot to supply the R code I tried:
vov1i2<-read.table("VOV1_INHIBITED6-16-2006-13h35min33sec.txt",header=TRUE)
test.lme<-lme(fixed=log2(Intensity)~End+logpgc,random=list(Probe=pdBlocked(list(~1,pdCompSymm(~1
),End=~1,ProbeNo=pdCompSymm(~1)),data=vov1i2)
It doesn't look right to me and it produces an error too.
It should be something around those lines though.
Tobias Guennel
Spencer Graves
2006-Jun-23 03:22 UTC
[R] Nested variance-covariance matrix in Multilevel model
What's your error message? I see a syntax error in
random=list(Probe=pdBlocked(list(~1,pdCompSymm(~1
),End=~1,ProbeNo=pdCompSymm(~1))
I count 5 open parens and 3 close parens. I know that might have
been part of what you copied into this email and not what you gave R.
However, it sounds like you have several problems.
Have you seen Pinheiro and Bates (2000) Mixed-effects models in S and
S-PLUS (Springer)? This is the premier (almost mandatory) reference for
'lme'. Moreover, the "~\library\nlme\scripts" subdirectory of
the R
installation directory (at least under Windows) contains files
"ch01.R",
"ch02.R", ..., "ch06.R", "ch08.R" containing
essentially all the S
commands used in the book, organized by chapter. This can save endless
hassles with spelling problems (and minor syntax differences between
S-Plus and R). Sections 1.5 and 1.6, pp. 40-72, discuss analyses if two
different nested experiments.
If just want a standard nested analysis, this should be adequate. If
you have other special things happening that I missed in skimming your
email, please explain why the analyses described in Pinheiro and Bates
do you apply. In doing so, please include a simple, self-contained
example showing what you tried and why you think it's not adequate.
Please don't send us a megabyte of data. Instead, please either (a)
modify an example from the book or some other R documentation or (b)
generate phony data with a very few lines of R code.
Hope this helps.
Spencer Graves
Tobias Guennel wrote:
> I completely forgot to supply the R code I tried:
>
vov1i2<-read.table("VOV1_INHIBITED6-16-2006-13h35min33sec.txt",header=TRUE)
>
test.lme<-lme(fixed=log2(Intensity)~End+logpgc,random=list(Probe=pdBlocked(list(~1,pdCompSymm(~1
> ),End=~1,ProbeNo=pdCompSymm(~1)),data=vov1i2)
>
> It doesn't look right to me and it produces an error too.
>
> It should be something around those lines though.
>
> Tobias Guennel
Tobias Guennel wrote:> Dear R community,
>
> I have trouble implementing a nested variance-covariance matrix in the
> lme function.
>
> The model has two fixed effects called End and logpgc, the response
> variable is the logarithm to base 2 of Intensity ( log2(Intensity) )
> and the random effects are called Probe and ProbeNo.
> The model has the following nesting structure: A Pixel is nested within
> the ProbeNo,the ProbeNo is within the ProbeEnd ( there are two ends for
> every probe), and the ProbeEnd is within the Probe.
>
> Now the problem I have is that the variance-covariance structure of the
> model is quite complex and I can not find the right syntax for fitting
> it in the lme function.
>
> The variance-covariance structure is a block diagonal matrix of the form,
> V1 0 0
> V= 0 V2 0
> 0 0 V3
>
> where V1...V3 are of the structure:
> v11 v12
> V1= and so on.
> v21 v22
>
> V1...V3 are assumed to have a compound symmetric variance-covariance
> structure and therefore the submatrices are of the form:
> Lambda Delta1 Delta1 ... Delta1
> Delta1 Lambda Delta1 ... Delta1
> v11=v22= .......
>
> Delta1 ..... Lambda
>
> Delta2 Delta2 Delta2 ... Delta2
> Delta2 Delta2 Delta2 ... Delta2
> v12=v21= .......
>
> Delta2 ..... Delta2
>
> The elements of these submatrices depend only upon the three covariance
> parameters: the compound symmetry parameter delta; the variance of
> random effect sigma^2g; and the residual variance sigma^2. I have
> formulas for the submatrices Lambda,Delta1 and Delta2 which I can't
> really paste in here.
>
> The SAS code dealing with this model is the following:
>
> proc mixed data=rnadeg.pnau;
> title 'CV structure for PNAU';
> class probepos probeno end probe pixelid newprobeid;
> model logPM=end logpgc / ddfm=satterth;
> random probeno newprobeid / subject=probe type=cs;
> lsmeans end / diff cl; run;
>
> Any ideas are appreciated a lot since I am kind of stuck at this point.
>
> Thank you
> Tobias Guennel
>
> ______________________________________________
> 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