Dear List, This is rather a theoretical question, but I was wondering if someone on the list can help me out. I have a dataset where at each spatial location I have a binary sequence of character presence/absence, so, for example at location A, I might have spatial coordinates xA=2390 and yA=1200, and a binary vector cA=c(0,0,0,1,1,0,1,0). I'm interested on evaluating the spatial structure of the binary vectors. The traditional approach would be the mantel test, where I compare the spatial distance matrix against the a binary distance matrix (e.g. Jaccard distance matrix), and I obtain a p-value through permutation. That will give me the correlation, but it won't give me structural properties that I'm interested in, namely sill and range. The mantel correlogram would give me something similar, but what I really would like to do is to fit a variogram model. Given that that the empirical variogram is half the euclidean distance between values at two points, can I use half the Jaccard distance (http://en.wikipedia.org/wiki/Jaccard_index) instead?
Many Thanks, Enrico [[alternative HTML version deleted]] _______________________________________________ R-sig-Geo mailing list R-sig-Geo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-geo