[R-sig-ME] Extract a variance estimate per level of random effect

[Luca Borger]

Hello,

I think there have been some recent papers on estimating individual 
variability in behaviour, but in any case is this useful?:

library(lme4)
fm1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy)
str(ranef(fm1, postVar = TRUE))
attr((ranef(fm1, postVar = TRUE))[[1]],"postVar")


HTH
Luca









# Forthcoming book chapter
# Dispersal Ecology and Evolution (ch. 17)
# http://ukcatalogue.oup.com/product/9780199608904.do
---------------------------------------------------------------------
Luca Borger
Postdoctoral Research Fellow
Centre d'Etudes Biologiques de Chizé
CNRS (UPR1934); INRA (USC1339)
79360 Villiers-en-Bois, France

Tel: +33 (0)549 09 96 13
Fax: +33 (0)549 09 65 26
email: lborger at cebc.cnrs.fr
Web: http://cnrs.academia.edu/LucaBorger
Researcher ID: http://www.researcherid.com/rid/C-6003-2008
Google Scholar: http://scholar.google.com/citations?user=D5CTvNUAAAAJ
---------------------------------------------------------------------
# Newly published! Animal Migration: A synthesis (ch. 8):
# http://ukcatalogue.oup.com/product/9780199568994.do

Le 18/06/2012 10:29, Samantha Patrick a écrit :
> Hi
>
> I am currently trying to estimate how consistent individuals are in a 
> trait.  I want to produce an estimate of the variability for each 
> level of a random effect (ID).  I can do this simply by calculation 
> the variance for each ID separately but I am trying to extract this 
> information from a mixed model (either in lmer or mcmcglmm).  I have 
> trawled the mailing list but can not find any answers.
>
> As an simplified dummy example I have 2 individuals, each with 5 
> observations of a trait.  I can calculate 2 variances, using the 5 
> observations for each individual.
>
> head(Data)
> ID    trait1
> 1        10
> 1        15
> 1        12
> 1        19
> 1        11
> 2        9
> 2        10
> 2        9
> 2        10
> 2        10
>
> Variance for 1 = 4.67
> Variance for 2 = 0.3
>
> Alternatively I can fit a model of:
>
> model1<-lmer(trait1 ~(1|ID))
>
> From the variance covariance matrix I can easily extract the between 
> and within group variances, but is there a way to extract individual 
> variance estimates?
>
> Many Thanks
>
> Sam
>