[R-sig-eco] fish density in GLMM - experimental design problem

[Krzysztof Sakrejda]

On Mon, Sep 23, 2013 at 8:11 AM, joana martelo <jmmartelo at fc.ul.pt> wrote:
> Dear list
>
>
>
> I'm trying to model the relationship between prey capture success by fish
> (binomial variable, 0/1)  and fish length (continuous), fish density (2,4
> and 6 individuals) and water velocity (8, 12 and 26cm/2) using GLMM with
> fish.id as a random effect. Capture success was collected during trials that
> consisted in sending a prey every 2 min, which could be captured or not by
> individual fish.
> A total of 20 prey was sent in each trial independently of
> fish density, therefore the probability of capture is higher in 2 fish
> trials than in 4 fish trials and any effect of density would be because of
> the experimental design!

So you have an experiment which measures how competition among individuals
affects per-individual capture  probability... what are you trying to
measure?  It's
hard to say anything useful when we don't know that.

> Do you know of any way I could incorporate this
> information in my models?
>
>
>
>
>
> Model1<-glmer(capture~ length + density+ velocity +
> (1|fish.id.),family=binomial,data=cap)
>
>
>
>
>
> Thanks in advance
>
>
>
> Best regards,
>
>
>
> Joana Martelo
>
>
>
>
>
>
>
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology



-- 

Krzysztof Sakrejda

Organismic and Evolutionary Biology
University of Massachusetts, Amherst
319 Morrill Science Center South
611 N. Pleasant Street
Amherst, MA 01003

work #: 413-325-6555
email: sakrejda at cns.umass.edu