[R-sig-Geo] bivariate pairwise interaction spatial point process

[Colin Robertson]

Hi Rolf,

Thanks for your reply. Yes I think the multitype Strauss model is what
I was looking for, with parameters (gammas) for interaction in
component 1, 2 and between 1 & 2, which I believe is the gamma matrix
parameter for straussm.

Apologies for my lack of clarity in the initial question, I was
looking at the model in Diggle pg 85 under Markov point processes.

Thanks again,

Colin





On Wed, May 25, 2011 at 4:39 PM, Rolf Turner <r.turner at auckland.ac.nz> wrote:
> On 26/05/11 07:58, Colin Robertson wrote:
>>
>> Dear List,
>>
>> I am looking for examples of how to simulate a bivariate pairwise
>> interaction point process. The only multivariate (type) model I can
>> find is the poisson multitype pattern in Spatstat. The Strauss process
>> can give me interaction point process, but I cannot see how to use it
>> to formulate a bivariate model.
>
> It's not clear to me what you're asking but does the "straussm"
> conditional intensity function for rmh() (multitype Strauss model)
> do what you want?
>
> See ?rmhmodel.default.
>
> If not, can you be more explicit about the model that you wish
> to simulate?
>
>    cheers,
>
>        Rolf Turner
>