R help - Aug 2008 - lme questions re: repeated measures & covariance structure

Hello,

We are attempting to use nlme to fit a linear mixed model to explain bird
abundance as a function of habitat:


lme(abundance~habitat-1,data=data,method="ML",random=~1|sampleunit)

The data consist of repeated counts of birds in sample units across multiple
years, and we have two questions:

1) Is it necessary (and, if so, how) to specify the repeated measure
(years)? As written, the above code does not.

2) How can we specify a Toeplitz heterogeneous covariance structure for this
model? We have searched the help file for lme, and the R-help archives, but
cannot find any pertinent information. If that's not possible, can we adapt
an existing covariance structure, and if so how?

Thanks, Mark

	[[alternative HTML version deleted]]

Dear Mark,

I would include the repeated measure as the smallest stratum in the random
effects specification:

random=~1|sampleunit/year

Setting up user-defined variance structures should be possible using for
example:

weights=varPower(form=~habitat)

or also try out the available corStruct() classes (found in Pinheiro and Bates
2000)

HTH
Christoph




Mark Na schrieb:
> Hello,
> 
> We are attempting to use nlme to fit a linear mixed model to explain bird
> abundance as a function of habitat:
> 
> 
>
lme(abundance~habitat-1,data=data,method="ML",random=~1|sampleunit)
> 
> The data consist of repeated counts of birds in sample units across
multiple
> years, and we have two questions:
> 
> 1) Is it necessary (and, if so, how) to specify the repeated measure
> (years)? As written, the above code does not.
> 
> 2) How can we specify a Toeplitz heterogeneous covariance structure for
this
> model? We have searched the help file for lme, and the R-help archives, but
> cannot find any pertinent information. If that's not possible, can we
adapt
> an existing covariance structure, and if so how?
> 
> Thanks, Mark
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 
> .
> 
-- 
Dr. rer.nat. Christoph Scherber
University of Goettingen
DNPW, Agroecology
Waldweg 26
D-37073 Goettingen
Germany

phone +49 (0)551 39 8807
fax   +49 (0)551 39 8806

Homepage http://www.gwdg.de/~cscherb1