Comparison of Root Mean Square Error

[MichaelHenkin]

I performed Ordinary Kriging interpolation on two elevation datasets. The first dataset represents all the field-collected elevation points, and the second dataset represents a 75% subset of the collected points. We are trying to come up with a new surveying method and wanted to explore changing the number of sample sites.

I wanted to know if there is a way to compare the two RMSE from the Cross-Validation beyond just which one is larger and which one is smaller. Is there a way to tell if these two values are statistically different? If so, any ideas on how to do this?

Thank you in advance for any help!

[EricKrause]

To do this, you would have to come up with some kind of distribution for root-mean-square crossvalidation errors.  Unfortunately, we're not aware of any valid way to do this (or if it's even possible).  If you ever come across a methodology for this, please let us know.