Hei, I have two spatial datasets Sa and Sb, both with lat-lon coordinates and from same geographic area, but from different localities within the area (independent samples). Sa is biotoc data, Sb is some environmental parameter (fertility). I 'know' that Sb affects Sa, but wonder on which scale. I tried different interpolations by creating different grids of Sb (e.g. 20x20 and 100x100 points using 'interp' ...) and found that a more coarse grid did a better job in predicting Sa than a high resolution grid. However, I wonder if there aren't more elegant ways, e.g. using kriging. Just to avoid misunderstandings: I do not just want to get a spatial grid of Sa and Sb, but I want to find on which Scale Sb affects Sa. cheers, Robert, Robert Ptacnik Norwegian Institute for Water Research (NIVA) Gaustadall?en 21 NO-0349 Oslo FON +47 982 277 81 FAX +47 221 852 00 ---------------------------------------------------------------------------------------------------------------------- NIVAs hovedkontor har flyttet til nye lokaler i CIENS - Forskningssenter for milj? og samfunn; Gaustadall?en 21, 0349 Oslo. Meld deg p? v?rt nyhetsbrev p? niva.no).
Hi Robert, A package I use for spatial statistics is gstat. It supports a method called co-kriging that seems to fit your needs. To get a good overview of the spatial capabilities of R a good place to start is the Spatial Task View (cran.r-project.org/web/views/Spatial.html). If you have more geo type questions the r-sig-geo list is a better forum (stat.math.ethz.ch/mailman/listinfo/R-SIG-Geo). cheers Paul robert.ptacnik at niva.no wrote:> Hei, > I have two spatial datasets Sa and Sb, both with lat-lon coordinates and > from same geographic area, but from different localities within the area > (independent samples). Sa is biotoc data, Sb is some environmental > parameter (fertility). I 'know' that Sb affects Sa, but wonder on which > scale. I tried different interpolations by creating different grids of Sb > (e.g. 20x20 and 100x100 points using 'interp' ...) and found that a more > coarse grid did a better job in predicting Sa than a high resolution grid. > However, I wonder if there aren't more elegant ways, e.g. using kriging. > Just to avoid misunderstandings: I do not just want to get a spatial grid > of Sa and Sb, but I want to find on which Scale Sb affects Sa. > cheers, > Robert, > > > Robert Ptacnik > Norwegian Institute for Water Research (NIVA) > Gaustadall?en 21 > NO-0349 Oslo > FON +47 982 277 81 > FAX +47 221 852 00 > > > > ---------------------------------------------------------------------------------------------------------------------- > NIVAs hovedkontor har flyttet til nye lokaler i CIENS - Forskningssenter > for milj? og samfunn; Gaustadall?en 21, 0349 Oslo. Meld deg p? v?rt > nyhetsbrev p? niva.no). > ______________________________________________ > R-help at r-project.org mailing list > stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >-- Drs. Paul Hiemstra Department of Physical Geography Faculty of Geosciences University of Utrecht Heidelberglaan 2 P.O. Box 80.115 3508 TC Utrecht Phone: +31302535773 Fax: +31302531145 intamap.geo.uu.nl/~paul