[ADMB Users] asreml ar(1) x ar(1) spatial model

[H. Skaug]

Hi All,

Mark is 100% right. The website and ADMB-RE manual needs to be
improved with respect to spatial modelling.
Let us start with the website. I have started by distinguish between
the two available approaches, see:

http://admb-project.org/examples/spatial-models

Can those of you interested in spatial modelling give me feedback on
what info should be added? Also
check out the geostatistical example:

http://admb-project.org/examples/spatial-models/glmm-with-spatial-structure-described-in-terms-of-covariance-function

What more do we need to say for users to understand?

The GMFR example is more complicated and a "brute-force" first (e.g.
on a 10x 10 matrix, so that it is feasible),"
example should be given. I will do that later.

Do people have other spatial models that we upload?

Any suggestion for how to improve the spatial examples are welcomed.

Hans


On Mon, Nov 28, 2011 at 9:50 AM, Mark Payne <mpa at aqua.dtu.dk> wrote:
> As a user who is struggling with spatial issues, I'd love to see this part of the ADMB website fleshed out more - potentially as a first step towards such a workshop. Kasper's example that is there at the moment is pretty dense and hard to make headway with for to those of us that are not familar with the finer points of spatial modelling...  Part of the problem I found is the sparse-matrix aspect of the example - maybe it could be good to have a simpler instructive example where it is done by "brute-force" first (e.g. on a 10x 10 matrix, so that it is feasible), and then have the sparse-matrix extension once people understand that.
>
> Another suggestion for a more general approach could be to build up a section on "incoporating correlation structures"? i.e. simple examples of how to do AR(1) processes, temporal and spatial correlations... The book by Zuur et al 2009 "Mixed Effects Models and Extensions in Ecology with R" has some nice examples in this direction that could easily be solved in ADMB as worked examples...
>
> Mark
>
>
>
> ________________________________________
> Fra: users-bounces at admb-project.org [users-bounces at admb-project.org] På vegne af H. Skaug [hskaug at gmail.com]
> Sendt: 26. november 2011 10:33
> Til: dave fournier
> Cc: users at admb-project.org
> Emne: Re: [ADMB Users] asreml ar(1) x ar(1) spatial model
>
> There are no examples with space-time models in the ADMB suite. (2dim
> space)x(time) makes
> 3 dimensions. It would be nice to have Dave's program extended in such a way.
>
> Maybe in the future there should be a course/workshop in spatial
> modeling in ADMB.
>
> Hans
>
> On Fri, Nov 25, 2011 at 11:50 PM, dave fournier <davef at otter-rsch.com> wrote:
>> On 11-11-25 02:29 PM, Mark Maunder wrote:
>>
>> Who is we?  Are we us?
>>
>> Anyway it is easy to add a third or fourth dimension to this.  The only
>> thing lacking
>> to make it really elegant is a random_effect_3darray so you have to use a
>> random effects matrix and calculate the offsets.
>>
>>> Dave,
>>>
>>> Do your models include time as a third dimension? This is where we are
>>> having difficulty with traditional methods.
>>>
>>> Mark
>>>
> _______________________________________________
> Users mailing list
> Users at admb-project.org
> http://lists.admb-project.org/mailman/listinfo/users
> _______________________________________________
> Users mailing list
> Users at admb-project.org
> http://lists.admb-project.org/mailman/listinfo/users
>