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

AI-GEOSTATS: How to use CV

Expand Messages
  • Ian Hunt [HQP]
    Dear List, I would appreciate a general discussion/recommendations on the use of the coefficient of variation (CV) in terms of sampling reliability firstly and
    Message 1 of 3 , Jan 21, 2004
      Dear List,

      I would appreciate a general discussion/recommendations on the use of the coefficient of variation (CV) in terms of sampling reliability firstly and secondly in the choice of when not to do ordinary kriging.

      The first case concerns the agricultural soil sampling situation where a farm is sampled and then the CV (on the raw data) is quoted locally as some form of reliability or risk figure. Does this make sense ? It seems that a farm with a high CV correlates to high variability in the farm and therefor high risk i.t.o crop estimates and crop modeling.

      In the second case some people have mentioned that a range of a CV of less than 0.5 is good for ordinary kriging and for bigger than 0.5 it is necessary to transform the data to logs or something else. What is a good practical number to use or what is a good tool to use for the choice of normality (including the use of the histogram and probability plot)

      Thanks in advance

      Ian Hunt

      --
      * 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
    • Syed Abdul Rahman Shibli
      I always thought the CV would be more useful as a means to compare two different distributions with dissimilar means. Two CVs measured at two different
      Message 2 of 3 , Jan 22, 2004
        I always thought the CV would be more useful as a means to compare two
        different distributions with dissimilar means. Two CVs measured at two
        different locations in the farm will indicate the relative dispersion
        between the two locations, since both standard deviations would be
        normalized by their mean values. Reading your post it's almost as if
        you're thinking of using it to determine if a distribution of values is
        skewed, for which the coefficient of skewness might be a better
        measure.

        Regards,

        Syed

        On 22 Jan 2004, at 06:30, Ian Hunt [HQP] wrote:

        > Dear List,
        >
        > I would appreciate a general discussion/recommendations on the use of
        > the coefficient of variation (CV) in terms of sampling reliability
        > firstly and secondly in the choice of when not to do ordinary kriging.
        >
        > The first case concerns the agricultural soil sampling situation where
        > a farm is sampled and then the CV (on the raw data) is quoted locally
        > as some form of reliability or risk figure. Does this make sense ? It
        > seems that a farm with a high CV correlates to high variability in the
        > farm and therefor high risk i.t.o crop estimates and crop modeling.
        >
        > In the second case some people have mentioned that a range of a CV of
        > less than 0.5 is good for ordinary kriging and for bigger than 0.5 it
        > is necessary to transform the data to logs or something else. What is
        > a good practical number to use or what is a good tool to use for the
        > choice of normality (including the use of the histogram and
        > probability plot)
        >
        > Thanks in advance
        >
        > Ian Hunt
        >
        > --
        > * 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


        --
        * 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
      • Isobel Clark
        Hi Ian The CV is useful if you are measuring things which can only take positive values and tend to be positively skewed - i.e. lumped towards the zero. In
        Message 3 of 3 , Jan 23, 2004
          Hi Ian

          The CV is useful if you are measuring things which can
          only take positive values and tend to be 'positively'
          skewed - i.e. lumped towards the zero. In that case,
          the standard deviation itself is not a measure of
          spread but something rather more complex. The CV is a
          simple measure of skewness under these conditions.

          In general:

          CV<1/3 might not be skewed

          CV around 1, moderately skewed

          CV much above 1, highly skewed

          The CV is directly related to the standard deviation
          of the logarithms in a lognormal situation.

          Does this help?

          Isobel Clark
          http://geoecosse.bizland.com/whatsnew.htm



          ________________________________________________________________________
          Yahoo! Messenger - Communicate instantly..."Ping"
          your friends today! Download Messenger Now
          http://uk.messenger.yahoo.com/download/index.html

          --
          * 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
        Your message has been successfully submitted and would be delivered to recipients shortly.