[R-sig-Geo] Multitype point pattern analysis

[Marcelino de la Cruz]

Maybe solutionset can help you. Try the followin example:

data(lansing)
lansing.spl <- split(lansing)
  blackoak <- with (lansing.spl, density.ppp(blackoak))
  hickory <- with (lansing.spl, density.ppp(hickory))
maple <- with (lansing.spl, density.ppp(maple))

# where density of maple is > 500 and density of hickory is > 500?
plot(solutionset(maple>500 & hickory>500))

# Three types case: where density of maple is > 500 and density of 
hickory is > 500 and density of blackoak > 100?
  plot(solutionset(maple>500 & hickory>500 & blackoak>100))

HTH

Marcelino




At 13:57 15/11/2009, Ervan Rutishauser wrote:
>Hi folk,
>
>I am working on tropical forest dynamic trying to find out "patches" 
>of young, adult or suppressed trees. Each tree has XY coordinates 
>and I consider my data as a multitype point pattern (ppt), handling 
>data with spatstat. Actually I consider each mark separately and 
>delineate areas of aggregation (contour(density(ppt)). Then, I 
>superimpose these high-density areas on the same map and look at 
>non-overlapping regions. This is not very satisfying and I would 
>like to go a step further in interpreting areas of e.g. low density 
>of adult trees and high density of suppressed trees. I could not 
>find any reference in the literature dealing with more than 2 types...
>
>Did anyone already deal with similar problem?? Any suggestion will 
>be greatly helpful.
>
>Thanks. Best,
>Ervan
>___________________________________________________________
>
>Ervan Rutishauser
>PhD student
>CIRAD - UMR AMAP
>BP 701
>97387 Kourou Cedex
>tel. 00594.594.32.92.96
>
>
>
>         [[alternative HTML version deleted]]
>
>_______________________________________________
>R-sig-Geo mailing list
>R-sig-Geo at stat.math.ethz.ch
>https://stat.ethz.ch/mailman/listinfo/r-sig-geo


***************************************
Marcelino de la Cruz Rot
Depto. Biologia Vegetal
EUIT Agricola
Universidad Politecnica de Madrid
28040-Madrid
SPAIN