Hi,
I have found that the model type used in Kriging can have a large influence on the RMSE of my model, but don't really understand how they work. For example, having ran lots of cross-validations with different data sets, I've found the K-Bessel model to yield the lowest RMSE, but cannot really explain why. I would like to briefly comment on the fundamentals of these models but cannot seem to find much information. Any links/references would be a great help, thank!
Dean