Loading ...
Sorry, an error occurred while loading the content.

[ai-geostats] on the calculation of total prediction variance

Expand Messages
  • Recep kantarci
    Hi Firstly I would like to thank E. Pebesma, P. Goovaerts and G. Dubois for valuable helps on “modelling trend”. One more question about the calculation of
    Message 1 of 1 , Jul 1, 2005
    • 0 Attachment

      Hi

       

      Firstly I would like to thank E. Pebesma, P. Goovaerts and G. Dubois for valuable helps on “modelling trend”.

       

      One more question about the calculation of total prediction variance.

       

      As known, total prediction variance is composed of two parts: one from kriging and one from trend.

      If UK or KED is used, total prediction variance can be calculated as given by Cressie (Statistics for Spatial Data, page 155).

      But, what if regression kriging (RK) is used at which the trend is modeled globally.

       

      The reason why I am asking this question is that in the report below authors calculates total prediction variance as in UK but they employ regression kriging.

       

      Isn’t there a distinction between UK and RK on calculation of variance?

       

      Hengl, T., Heuvelink, G.B.M. and Stein, A., 2003. Comparison of kriging
      with external drift and regression-kriging. Technical report,
      International Institute for Geo-information Science and Earth
      Observation (ITC), Enschede, pp. 18.
      http://www.itc.nl/library/Papers_2003/misca/hengl_comparison.pdf
        
      Best regards
      Recep


      Yahoo! kullaniyor musunuz?
      Simdi, 1GB e-posta saklama alani sunuyor
      http://tr.mail.yahoo.com
    Your message has been successfully submitted and would be delivered to recipients shortly.