R help - Oct 2005 - Help with Subtracting an effect from a Mixed Model

Hi Everyone,

I posted a similar question about a week ago, but haven't gotten any 
replies -- I'm afraid that's because my previous question was too 
vague.  Let me try again with a more specific question, and I hope 
someone can help.  NOTE, I know I should be using the newer lme4 
package, I just haven't had a chance to update my version of R yet, so 
the question below relates to nmle.

I have data from a classical quantitative genetics experiment, with 33 
sires mated each to 2 dams, with 15 progeny from each dam raised on 5 
host plants (3 larvae per host).  So the model I would like to run has 
the following factors:
Host (fixed)
Sire (random)
Dam [nested within sire] (random)
Host * Sire (random interaction)
Host * Dam [nested within sire] (random interaction)

This is the code I am using for that complete model:
lme1=lme(gain~host,random=~host|sire/dam)
I would like to try the model with and without each of those random 
interactions (host*sire and host*dam-nested-within-sire).

WHAT IS THE SYNTAX FOR SUBTRACTING AN EFFECT FROM THE RANDOM STATEMENT?
I have tried:
lme1=lme(gain~host,random=~host|sire/dam-sire:host)
But I get an "Invalid formula for groups" error.
Alternatively, I tried reorganizing the code, so that the interaction 
would be left out.  But there is no way to take out host*sire while 
still leaving in host*dam nested within sire.

any help will be greatly appreciated!
Matt

- - -
Matthew L Forister
Department of Ecology and Evolution
State University of New York at Stony Brook
650 Life Sciences Building
Stony Brook, New York 11794-5245
Email: forister at life.bio.sunysb.edu
Webpage: http://life.bio.sunysb.edu/~forister/
Lab phone: (631) 632-8609
Fax: (631) 632-7626
- - -

1.  Have you considered specifying the random effect as a list?  This 
is mentioned in the help file and discussed in Pinheiro and Bates (2000) 
Mixed-Effects Models in S and S-Plus (Springer).  On p. 40, they discuss 
the following example that might help you:

lme(pixel~day+day^2, data=Pixel, random=list(Dog=~day, Side=~1).

(I highly recommend this book, by the way.)

	  2.  Doug Bates has made several contributions to this within the past 
year or so, which you can find by purusing the documentation for the 
functions in the lme4 and using RSiteSearch.  The following was useful 
for me with an apparently similar issue: 
"http://finzi.psych.upenn.edu/R/Rhelp02a/archive/47423.html".

	  3.  If you'd like further help from this list, I encourage you to 
read the posting guide, "www.R-project.org/posting-guide.html", 
especially the part about submitting a self-contained toy example that 
illustrates your question.  If someone can copy a few lines of code from 
your email into R and try a few things in a couple of minutes, I believe 
it will increase the chances that you will get quick, useful answers.

	  hope this helps.
	  spencer graves	

Matthew Forister wrote:
> Hi Everyone,
> 
> I posted a similar question about a week ago, but haven't gotten any 
> replies -- I'm afraid that's because my previous question was too 
> vague.  Let me try again with a more specific question, and I hope 
> someone can help.  NOTE, I know I should be using the newer lme4 
> package, I just haven't had a chance to update my version of R yet, so 
> the question below relates to nmle.
> 
> I have data from a classical quantitative genetics experiment, with 33 
> sires mated each to 2 dams, with 15 progeny from each dam raised on 5 
> host plants (3 larvae per host).  So the model I would like to run has 
> the following factors:
> Host (fixed)
> Sire (random)
> Dam [nested within sire] (random)
> Host * Sire (random interaction)
> Host * Dam [nested within sire] (random interaction)
> 
> This is the code I am using for that complete model:
> lme1=lme(gain~host,random=~host|sire/dam)
> I would like to try the model with and without each of those random 
> interactions (host*sire and host*dam-nested-within-sire).
> 
> WHAT IS THE SYNTAX FOR SUBTRACTING AN EFFECT FROM THE RANDOM STATEMENT?
> I have tried:
> lme1=lme(gain~host,random=~host|sire/dam-sire:host)
> But I get an "Invalid formula for groups" error.
> Alternatively, I tried reorganizing the code, so that the interaction 
> would be left out.  But there is no way to take out host*sire while 
> still leaving in host*dam nested within sire.
> 
> any help will be greatly appreciated!
> Matt
> 
> - - -
> Matthew L Forister
> Department of Ecology and Evolution
> State University of New York at Stony Brook
> 650 Life Sciences Building
> Stony Brook, New York 11794-5245
> Email: forister at life.bio.sunysb.edu
> Webpage: http://life.bio.sunysb.edu/~forister/
> Lab phone: (631) 632-8609
> Fax: (631) 632-7626
> - - -
> 
> ______________________________________________
> 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
-- 
Spencer Graves, PhD
Senior Development Engineer
PDF Solutions, Inc.
333 West San Carlos Street Suite 700
San Jose, CA 95110, USA

spencer.graves at pdf.com
www.pdf.com <http://www.pdf.com>
Tel:  408-938-4420
Fax: 408-280-7915