[ADMB Users] estimation of random effects correlations

[Mollie Brooks]

Hi Kristian,

The default is to fit uncorrelated random effects (a diagonal variance-covariance matrix), but it appears that you can fit them with a full variance-covariance matrix using the corStruct argument. I can not testify to how well this has been tested.


corStruct	
a string specifying the covariance structure of the random effects vector. Two types of covariance matrices are currently implemented: "diag" (diagonal matrix) and "full" (positive definite matrix with all elements being estimated).


cheers,
Mollie

Mollie Brooks, PhD
Postdoctoral Researcher, Population Ecology Research Group, Ozgul Lab, http://www.popecol.org
Institute of Evolutionary Biology & Environmental Studies, University of Zürich



On 7 May 2013, at 9:39 AM, Kristian Kleinke <kmkleinke at gmail.com> wrote:

> Hi, 
> 
> just a short question I've been trying to find an answer to: 
> am I correct, that glmmadmb() cannot estimate correlations between random effects?
> 
> Thanks, 
> Kristian
> _______________________________________________
> Users mailing list
> Users at admb-project.org
> http://lists.admb-project.org/mailman/listinfo/users
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.admb-project.org/pipermail/users/attachments/20130507/8430c5f7/attachment.html>