Hi all, I'm doing a project for my course, and I got stuck understanding the requirements of the project. The project ask me to use 4 ways to do the spatial prediction: regression-based predictors (no spatial component), ordinary kriging (no regression component), universal kriging (regression trend and spatially correlated residuals), and nearest neighbours or inverse distance( no modeling of spatial correlation). I was totally confused about the with or without spatial component part, especially for the first and last method. It made me very depressed because I check a lot of materials and still don't get it, and I think maybe I just didn't understand the whole point of spatial statistics. I'm really appreciated if anybody can explain the difference of these different prediction methods!
Bingjie [[alternative HTML version deleted]] _______________________________________________ R-sig-Geo mailing list R-sig-Geo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-geo