Dear all, I have a data set consisting of estimates of fish density (Kg/m2) at intervals of about 30 km apart. I also have measurements of bottom depth at the same locations. I want to test the hypothesis that fish density depends on depth, being highest at the optimal depth for the species and declining at shallower and deeper depths. Under a non-geographical approach, I would fit a model to the data on fish density including depth, and compare the fit to one that does not include depth in it (constant mean). However, I cannot find out how to do this "correctly" with geographically-dependent data. I found several references on how to perform interpolation on a grid based on e.g. Universal Krigging with an external model, but I cannot see how to do this particular task. Any pointers would be greatly appreciated. -- View this message in context: http://r-sig-geo.2731867.n2.nabble.com/testing-hypotesis-about-species-distribution-Newbie-tp7580127.html Sent from the R-sig-geo mailing list archive at Nabble.com.
testing hypotesis about species distribution - Newbie
1 message · PCB