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

GEOSTATS: summary of kriging in binary fields.

Expand Messages
  • Victor De Oliveira
    Dear ai-geostat members, This note is a summary of the responses I received regarding my query about kriging in binary fields. Many thanks to J. Felipe Costa,
    Message 1 of 2 , May 7, 1997
    • 0 Attachment
      Dear ai-geostat members,

      This note is a summary of the responses I received regarding
      my query about kriging in binary fields. Many thanks to
      J. Felipe Costa, Goovaerts Pierre, Marcia Gumpertz, Alaa Ali,
      Samantha Low Choy, and Benjamin S. Warr.

      Here is a summary of their replys.

      J. Felipe Costa mentions simulation techniques as
      sequential indicator kriging and multigaussian truncated simulation in
      order to deal with categorical variables. He suggests looking at
      the 4th and 5th Int. Geostatistical Congress Proceedings, thouht the last
      has not appeard yet.

      Goovaerts Pierre has a paper where the indicator approach is used
      for categorical variables, Goovaerts (1996),Math. Geol., Vol. 28, p.909-921.,
      and adds the reference Soares (1992).
      He also wrote a book, which will be out in late July,
      "Geostatistics for Natural Resources Evaluation", costs $59.95 and will be published by Oxford University Press. In there it is explain techniques to
      deal with categorical variables.

      Marcia Gumpertz mentions the reference:
      Albert, P. S. and McShane, L. M., 1995, A generalized estimating equations
      approach for spatially correlated binary data:
      applications to the analysis of neuroimaging data, Biometrics, 51: 627-638

      Alaa Ali wrote an extensive and informative reply, which was sent to
      the whole list.

      Samantha Low Choy is working in her PhD dissertation on modelling spatial
      dependence using binary markov random fields, which is scheduled to be
      finish in November.

      Benjamin S. Warr mentions that indicator kriging is not simply for thresholded
      variables, but also works well with categorical data, if, and only if they
      are assumed to represent an ordered multi-state categorisation. He adds the
      reference Burrough and Bierkins, Indicator Geostats for categorical soil data,
      somewhere in the European Journal fo Soil Science, and
      finally Isaaks and Srivastava say something to this effect.

      Thanks once again to all whom replied.
      Regards.

      Victor De Oliveira
      Dapartment of Mathematics
      University of Maryland
      College Park, MD 20742
      USA

      vdo@...



      --
      *To post a message to the list, send it to ai-geostats@....
      *As a general service to list users, please remember to post a summary
      of any useful responses to your questions.
      *To unsubscribe, send email to majordomo@... with no subject and
      "unsubscribe ai-geostats" in the message body.
      DO NOT SEND Subscribe/Unsubscribe requests to the list!
    • Ashley Francis
      -- *To post a message to the list, send it to ai-geostats@gis.psu.edu. *As a general service to list users, please remember to post a summary of any useful
      Message 2 of 2 , May 8, 1997
      • 0 Attachment
        --
        *To post a message to the list, send it to ai-geostats@....
        *As a general service to list users, please remember to post a summary
        of any useful responses to your questions.
        *To unsubscribe, send email to majordomo@... with no subject and
        "unsubscribe ai-geostats" in the message body.
        DO NOT SEND Subscribe/Unsubscribe requests to the list!
      Your message has been successfully submitted and would be delivered to recipients shortly.