Skip to content

Random formula

3 messages · De Smedt Sebastiaan, ONKELINX, Thierry, Luca Borger

Original
ONKELINX, Thierry
# 
Dear Sebastiaan,

Models with nested random effects can be done with nlme. Have a loot at
section 4.2.3 of Pinheiro and Bates (2000) Mixed effects models in S and
S-plus.

You will need something like

lme(response ~ climate_factor*pruning, random = list(provenance = ~
pruning, tree = ~1))

HTH,

Thierry

------------------------------------------------------------------------
----
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature
and Forest
Cel biometrie, methodologie en kwaliteitszorg / Section biometrics,
methodology and quality assurance
Gaverstraat 4
9500 Geraardsbergen
Belgium
tel. + 32 54/436 185
Thierry.Onkelinx at inbo.be
www.inbo.be

To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to
say what the experiment died of.
~ Sir Ronald Aylmer Fisher

The plural of anecdote is not data.
~ Roger Brinner

The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of
data.
~ John Tukey

-----Oorspronkelijk bericht-----
Van: r-sig-mixed-models-bounces at r-project.org
[mailto:r-sig-mixed-models-bounces at r-project.org] Namens De Smedt
Sebastiaan
Verzonden: maandag 15 juni 2009 16:23
Aan: r-sig-mixed-models at r-project.org
Onderwerp: [R-sig-ME] Random formula

Hi,

I measured leaf characteristics. The leaves are grouped in trees which
are, on their turn, grouped in provenances.
I want to model those leaf characteristics in function of climate
variables (measured on provenance level) and pruning characteristics
(measured on tree level). I also want to see if the effect of pruning
differs between provenances (provenance-pruning interaction).
The problem is that there cannot be an interaction between pruning and
tree, because pruning is measured on tree level. 

in lme4, I think I can specify this model as follows:

response ~ climate_factor*pruning + (pruning|provenance) +
(1|provenance/tree)

Or is there another way?

Is it possible to define this model in the nlme library (I need a
variance structure, which doesn't exist in lme4)?

Thanks a lot!
Sebastiaan

Sebastiaan De Smedt
Department of Bioscience Engineering
University of Antwerp
Belgium
Tel.: +32 (0)3 265 35 17
Fax.: +32 (0)3 265 32 25


_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer 
en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is
door een geldig ondertekend document. The views expressed in  this message 
and any annex are purely those of the writer and may not be regarded as stating 
an official position of INBO, as long as the message is not confirmed by a duly 
signed document.
Luca Borger
# 
Hello,

given that you are fitting a gaussian response model and that your random 
effects are strictly nested (if I understand it correctly), nlme can be used 
easily (unless I get corrected by the experts on the list). You could fit 
them:

# m1, no random slope
response ~ climate_factor*pruning,
    random = list(provenance =~ 1, tree =~ 1),


# m2, random slope for pruning at provenance level
response ~ climate_factor*pruning,
    random = list(provenance =~ pruning, tree =~ 1),



HTH


Cheers,

Luca


----- Original Message ----- 
From: "De Smedt Sebastiaan" <Sebastiaan.DeSmedt at ua.ac.be>
To: <r-sig-mixed-models at r-project.org>
Sent: Monday, June 15, 2009 10:22 AM
Subject: [R-sig-ME] Random formula