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

[ai-geostats] comparing variograms?

Expand Messages
  • George R Cutter
    Dear ai-geostats Members, Are there appropriate statistical tests for determining whether empirical variograms are statistically different (maybe something
    Message 1 of 3 , Oct 15, 2004
    • 0 Attachment
      Dear ai-geostats Members,

      Are there appropriate statistical tests for determining whether empirical
      variograms are statistically different (maybe something akin to a
      Kolmogorov-Smirnoff or chi-square test)?

      Is there a test for comparing variogram model parameters?

      If not, why? If so, what assumptions are required?

      Does anyone know of a published reference where such comparisons have been made?

      Thank you,
      Randy Cutter.

      -------------------------------------
      University of New Hampshire
      Center for Coastal and Ocean Mapping
      Chase Ocean Engineering Lab,
      24 Colovos Rd., Durham, NH 03824
      Phone 603-862-0564 Fax 603-862-0839
      email - gcutter@...
      CCOM website: http://www.ccom.unh.edu
      -------------------------------------
    • José-Manuel Blanco-Moreno
      Hello, Try: SCHABENBERGER O & PIERCE FJ (2002) Contemporary statistical models for the plant and soil sciences. CRC Press, Boca Raton, Florida. They compare
      Message 2 of 3 , Oct 18, 2004
      • 0 Attachment
        Hello,
        Try:
        SCHABENBERGER O & PIERCE FJ (2002) Contemporary statistical models for
        the plant and soil sciences. CRC Press, Boca Raton, Florida.

        They compare theoretical semivariograms between treatments through non
        linear regression. They use something like to the extra sum of squares.
        Details on this one on:
        RATKOWSKY DA (1983) Nonlinear Regression Modeling: a Unified Practical
        Approach. M. Dekker, New York.

        However, it does not convince me. From my point of view, comparisson of
        spatial structures through non linear regression is a kind of artifact.

        And remember:
        “He uses statistics as a drunken man uses lamp-posts... for support
        rather than illumination." - Andrew Lang
        or
        "Statistics are like bikinis. What they reveal is suggestive, but what
        they conceal is vital" - Aaron Levenstein
        or
        "Torture numbers, and they'll confess to anything" - Gregg Easterbrook



        George R Cutter wrote:

        >Dear ai-geostats Members,
        >
        >Are there appropriate statistical tests for determining whether empirical
        >variograms are statistically different (maybe something akin to a
        >Kolmogorov-Smirnoff or chi-square test)?
        >
        >Is there a test for comparing variogram model parameters?
        >
        >If not, why? If so, what assumptions are required?
        >
        >Does anyone know of a published reference where such comparisons have been made?
        >
        >Thank you,
        >Randy Cutter.
        >
        >-------------------------------------
        >University of New Hampshire
        >Center for Coastal and Ocean Mapping
        >Chase Ocean Engineering Lab,
        >24 Colovos Rd., Durham, NH 03824
        >Phone 603-862-0564 Fax 603-862-0839
        >email - gcutter@...
        >CCOM website: http://www.ccom.unh.edu
        >-------------------------------------
        >
        >
        >

        --
        José Manuel Blanco Moreno
        Ph.D Student

        ---------------------------------------
        José-Manuel Blanco-Moreno

        Dept. de Biologia Vegetal (Botànica)
        Universitat de Barcelona
        Av. Diagonal 645
        08028 Barcelona
        SPAIN
        ---------------------------------------

        phone: (+34)93.402.1471
        fax: (+34)93.411.2842
        e-mail: jmblanco@...
      • Pat Bellamy
        Try Lark, R.M. 2000. A comparison of some robust estimators of the variogram for use in soil survey. European Journal of Soil Science 51, 137-157. This paper
        Message 3 of 3 , Oct 18, 2004
        • 0 Attachment
          Try Lark, R.M. 2000. A comparison of some robust estimators of the variogram for use in soil survey. European Journal of Soil Science 51, 137-157. This paper gives a method of testing wether a variogram is 'correct' or not - ie not overestimated due to outliers etc.

          Pat Bellamy


          Mrs Pat Bellamy B.Sc. M.Sc.
          Statistician/Computer Analyst
          National Soil Resources Institute (NSRI),
          Cranfield University at Silsoe,
          Silsoe,Bedfordshire,
          MK45 4DT,
          UK
          -------------------------------------------------------------------
          Tel.: +44.(0)1525.863260 (direct)
          Fax.: +44.(0)1525.863253
          Email: p.bellamy@...
          http://www.cranfield.ac.uk/nsri/



          -----Original Message-----
          From: George R Cutter [mailto:gcutter@...]
          Sent: 15 October 2004 18:42
          To: ai-geostats@...
          Subject: [ai-geostats] comparing variograms?


          Dear ai-geostats Members,

          Are there appropriate statistical tests for determining whether empirical
          variograms are statistically different (maybe something akin to a
          Kolmogorov-Smirnoff or chi-square test)?

          Is there a test for comparing variogram model parameters?

          If not, why? If so, what assumptions are required?

          Does anyone know of a published reference where such comparisons have been made?

          Thank you,
          Randy Cutter.

          -------------------------------------
          University of New Hampshire
          Center for Coastal and Ocean Mapping
          Chase Ocean Engineering Lab,
          24 Colovos Rd., Durham, NH 03824
          Phone 603-862-0564 Fax 603-862-0839
          email - gcutter@...
          CCOM website: http://www.ccom.unh.edu
          -------------------------------------
        Your message has been successfully submitted and would be delivered to recipients shortly.