[R-sig-Geo] [R] Spatial data, rpoispp, using window with fixed radius?

[Adrian.Baddeley at csiro.au]

The following message appeared on R-help but this discussion should be moved to R-sig-geo 

On 07/01/12 02:17, herbert8686 at gmx.de wrote:

> I was searching through the spatstat manual in order to find a function
>  to simulate a Poisson pattern only within a fixed radius (circular moving window)
 > around individual points. If points are distributed heterogeneously over a 
> large area this may help to only assess deviation from CSR within the window 
> and thus does not require additional information on a covariate. 
> I could not find such a function in spatstat. Can please anyone help?

What do you want to happen if two of the circles overlap? Should the density of random points be twice as high? 

If the answer is 'yes' then do the following (where X is your original point pattern of centres, and 'r' is the radius of the circles, and 'lambda' is the intensity of random points per unit area in each circle)

       V <- scanmeasure(X, r)
       V <- eval.im(lambda * V)
       Y <- rpoispp(V)

If the answer is 'no' then do 
       W <- dilation(X, r)
       Y <- rpoispp(lambda, win=W)

Adrian Baddeley