gaiarrido <gaiarrido <at> usal.es> writes:
> When I try to adjust a mixed model with random effects I can make this
order
> without problem
>
> > lm.FA<-lme(absFA~trait*condition,random=~1|individual)
>
> But if I try to fit a model in which the response (absFA) is not the same
in
> all individuals at different levels of "trait" factor , but
varies randomly
> from each. That is, this order
>
> > lm.FA2<-lme(absFA~rasgo*condicion,random=~rasgo|individuo)
>
> R hangs and crashes, I've tried both with R 2.13 and with R 2.15.
>
This is not reproducible ... and would be better on the
r-sig-mixed-models <at> r-project.org list. If/when you repost,
more details would be useful:
* how big is your data set (number of individuals, total
number of observations)?
* are you including a data= argument in your calls? It is
generally considered good practice.
* your predictor variables are different in the two calls --
are you using different data sets, or different predictors,
(i.e. 'condicion' vs 'condition', 'individual' vs
'individuo',
'rasgo' vs 'trait'), or is this a typo?
* have you checked to see that all variables are of the type
you think they should be (numeric vs factor)?
* do you actually have multiple observations with different
trait values within at least some individuals?
* see <http://tinyurl.com/reproducible-000>, or the posting
guide, for information about reproducible examples ...