[R] mpl in spatstat

rohan sadler rsadler at agric.uwa.edu.au
Thu May 1 05:07:58 CEST 2003

Hi Suzanne,

It sounds like you are dealing with an Inhomogeneous Poisson Point 
Process (the simplest). The intensity function lambda(mu) of this 
process is the density of points near mu. i.e. the process is poisson 
locally, and the intensity varies over the region according to some 
underlying function or surface (such as soil chemistry)

 > plot(rpoispp(function(x,y){300*cos(2*pi*x)},300))  # taken from 
Adrian Baddeley's notes

The first step would then be interpolate your soil characteristics into 
global functions (either through delaunay triangulation, smoothing 
method (loess), or krigging). This allows you to estimate soil 
characteristics where your trees are, and derive vectors of the same 
length (although with some error).

There may also be away of involving the idea of a global funciton into 
the actual inference process, but I haven't thought about that deeply 
and my memory cells aren't stirred to recall a suitable reference.

Hope this was of some use.

Rohan Sadler

Suzanne E. Blatt wrote:

>Hello all,
>I'm attempting to conduct spatial analysis of trees within a plot.  I want to see if the trees are spatially correlated to soil characteristics, say pH, or   moisture content.  I think one way to do it is with mpl, however, my soil characteristics were not taken at exactly the same locations as my trees and further, the vectors aren't the same length.  I'm getting the impression, largely from the error messages, that length matters, ie. they must be the same.  In my case this is impossible.  The example listed in the file:///tmp/Rtmp1608/.R/library/spatstat/html/mpl.html regarding 'soilsurvey' using 'soilchem' as the covariate does not seem to be located in library(spatstat) nor library(splancs).  I'm trying to see how that example works, but can't locate it.  Can anyone tell me how to circumvent the 'length' problem or direct me to the location of 'soilsurvey' and 'soilchem' so I can see how those datasets are set up.
>__________________________________________________________________Try AOL and get 1045 hours FREE for 45 days!http://free.aol.com/tryaolfree/index.adp?375380
>R-help at stat.math.ethz.ch mailing list

PhD Student, Ecosystems Research Group (ERGO)
School of Plant Biology (Botany), Faculty of Natural & Agricultural Sciences,
The University of Western Australia, 35 Stirling Highway, Crawley  WA  6009, Australia

Ph:  +61 8 9380 7914
Fax: +61 8 9380 7925
email: rsadler at agric.uwa.edu.au
ERGO's web site:<http://www.botany.uwa.edu.au/ergo>

More information about the R-help mailing list