AI-GEOSTATS: Comparing spatial interpolators
- Hi again,
after I got so much response to my questions concerning spaital
interpolation comparison I want to present to you my conclusion:
It seems to be a very big problem to make qualitatively assumtions on the
goodness of a spaital interpolator compared to another. Nevertheless, many
ecological relevant studies use cross-validation to perform this check
(using RMSE, MAE or MRE for their pursoses). In literature we find the
advice that quantitative assumtions can be made like this e.g. (how many
locations are over or underestimated etc.) but qualitative comparision can
be misleading. Therefore I propose the follwoing:
1. Check crossvalidation results for a firsdt comparison
2. Count the numer of sites of misesimation
3. Calculate the largest differences between the estimated and true values
4. Perform a t-test for independet variables
5. Calculate the regression coefficient between estimated and true values
(output = r2)
6. Look with your expert knowledge at the maps produced and interprete the
Now I am very much intersted in your opinion concerning this proceeding.
Would you say this is a correct comparison of a spatial interpolator ?
Schützen Sie Ihren Posteingang vor unerwünschten E-Mails.
http://www.msn.de/antispam Jetzt Hotmail-Junk-Filter aktivieren!
* To post a message to the list, send it to ai-geostats@...
* As a general service to the users, please remember to post a summary of any useful responses to your questions.
* To unsubscribe, send an email to majordomo@... with no subject and "unsubscribe ai-geostats" followed by "end" on the next line in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the list
* Support to the list is provided at http://www.ai-geostats.org