On Oct 24, 2010, at 6:12 AM, Lorenzo Isella wrote:
As to the domain of the function, at least in case (1), that should arise from the collected data points in (x,y) if the sampling is dense enough.
And that is precisely what you get from the perimeter function. The earlier Design package provided an those facilities in base graphics. The paradigm for plotting regression objects changed a bit when Harrell shifted over to Lattice, but he has always provided worked examples that generalize nicely to real situations.
There are also som nice examples of contourplots constrained to geographic regions in Woods' text on generalized additive models. I'm sure the spatial stats people have such facilities as well.
Cheers Lorenzo
______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.