[ai-geostats] Re: about cross-validation
- HiPrior to 1983, most people used cross validation to check whether their kriging methods were working or to compare one kriging method with another. After that, most references are to checking back on the semi-variogram model.You can start with my 1986 paper, "The art of cross validation", which can be downloaded at http://uk.geocities.com/drisobelclark/resume (follow publications link) and/or the 1979 paper "Does geostatistics work?",Isobel
"M. Nur Heriawan" <mn_heriawan@...> wrote:
One of my colleague asked me about the mathematical
equation of cross-validation method (leave-one-out
method), and I said that it depends on the estimation
method he used. He wants to know the general
mathematical equation to define a cross-validation
So far, in my experience, such method is performed
just to check...which variograms model we used in
(kriging) estimation are correct (valid).
But cross-validation method should be used also to
check the validation of any kind of estimation methods
May someone address me to a reference or book
discussed in detail about cross-validation
(leave-one-out) method, especially in mathematical
point of view. Any kind of information related to this
method is also appreciated.
Many thanks for kind attention.
Earth Resources Exploration Research Group
Faculty of Earth Sciences and Mineral Technology
Institut Teknologi Bandung (ITB), Indonesia
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
* By using the ai-geostats mailing list you agree to follow its rules
( see http://www.ai-geostats.org/help_ai-geostats.htm )
* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...