[R-sig-Geo] NA values when fitting IPP model involving a spatial covariate {spatstat}

Robin W Hunnewell rhunne at mac.com
Fri Oct 7 15:22:51 CEST 2011


Dear all, 

I'm working with function 'ppm' in pkg: spatstat; the aim is to fit IPP (inhomogeneous pt process) model to a point pattern.
It's worked well before, but recently have tried it with an additional covariate -- spatially referenced and stored as an image object.
When I go to run the inhom point process model, the following warning appears. 'B10' is my point pattern object, 'flightPix' is the spatial covariate image object.

> Q <- ppm(B10, ~flights, covariates = list(flights = flightPix))
Warning message:
Values of the covariate ‘flights’ were NA or undefined at 0.08% (2 out of 2493) of the quadrature points. Occurred while executing: ppm(B10, ~flights, covariates = list(flights = flightPix)) 

# then when I look at summary output for the IPP model, it says:
Problem:
 Values of the covariate ‘flights’ were NA or undefined at 0.08% (2 out of 2493) of the quadrature points 

Is there a way solve this problem? Thanks for any help!!
Robin
-------------
Department of Biology
University of New Brunswick
Fredericton, NB  
Canada 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-geo/attachments/20111007/188608a5/attachment.html>


More information about the R-sig-Geo mailing list