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

Re: [ai-geostats] Spatial analysis

Expand Messages
  • Koen Hufkens
    ... A figure would be nice to interpretate the situation. Put it on some website, this makes it easier for people to access it if they want to and links are
    Message 1 of 5 , Aug 6, 2004
    • 0 Attachment
      >Is there a way I can characterise the variability at each spatial scale that would allow me to compare both between scales for each plot and between the plots?
      >
      >
      A figure would be nice to interpretate the situation. Put it on some
      website, this makes it easier for people to access it if they want to
      and links are accepted by the maillinglist server.

      I had a similar problem and I used a Moran's I index, as far as I know
      the most simple test you can do and it can me automated. You could
      calculate the index for every scale and compare scales in and between
      plots and you can calculate them for every plot to compare plots.

      This is the quick and easy approach to the problem I would use... but
      who am I...

      Good luck with your analysis,
      Koen.
    • Monica Palaseanu-Lovejoy
      Hi, It is true that the general consensus is that you need at least 50 to 100 points for a stable semi-variogram, but myself i bent this rule a little and i
      Message 2 of 5 , Aug 6, 2004
      • 0 Attachment
        Hi,

        It is true that the general consensus is that you need at least 50 to
        100 points for a stable semi-variogram, but myself i bent this rule a
        little and i worked with 35 points ....

        But you can use LISA (Local Indicators of Spatial Association -
        LISA, 1995, by Luc Anselin, geographical Analysis 27 (2), pp 93 -
        115). LISA is implemented in GeoDA freely available from
        http://sal.agecon.uiuc.edu/default.php

        GeoDa is very friendly and easy to use, but you need to be at least
        a little familiar with ESRI products (ArcView or ArcGIS) and
        especially shape files.

        You can also use sdep package from R (http://cran.r-project.org/) -
        which is a free statistical software - very powerful but with a very
        steep curve of learning.

        The idea is to use local indicators such as local Moran's I and local
        Gearry c for investigating local spatial instabilities (homogeneity
        versus heterogeneity).

        I hope this helps,

        Monica


        Monica Palaseanu-Lovejoy
        University of Manchester
        School of Geography
        Mansfield Cooper Bld. 3.21
        Oxford Road
        Manchester M13 9PL
        England, UK
        Tel: +44 (0) 275 8689
        Email: monica.palaseanu-lovejoy@...
      • Gregoire Dubois
        Good day everyone ! It is true that the general consensus is that you need at least 50 to 100 points for a stable semi-variogram, but myself i bent this rule
        Message 3 of 5 , Aug 7, 2004
        • 0 Attachment
          Good day everyone !

          "It is true that the general consensus is that you need at least 50 to
          100 points for a stable semi-variogram, but myself i bent this rule a
          little and i worked with 35 points .... "

          .... and I even worked with 9 or 10 points recently (how shocking !).

          It is true that one of the favourite comments made by reviewers (those
          unexperienced in geostatistics) is "how many points do you need/did you
          use" and the favourite reply of the authors is almost systematically
          "there is a rule of thumb about this matter... 30 pairs of points is a
          minimum" followed by a reference to Cressie's book. Such a reply is a
          convenient way to get around the discussion. I must admit, I also used
          the same reference to avoid wasting time and space with discussions that
          would distract the reader from the main argument treated.

          Practically, the number of points you need to describe a spatial
          correlation is very much depending on your experience with the
          phenomenon you study. If you expect a strong correlation (because of
          previous case studies, litterature) and see such a correlation, even if
          calculated on very few observations, why not trust your results? If you
          don't see anything, than you could consider increasing your sample size.
          Few observations will obviously not lead you to results that are
          statistically robust but they may be enough to confirm your assumptions.
          I believe everyone who has a bit of experience in geostatistics has been
          impressed by the large amount of silly semi-variograms published in peer
          reviewed papers: even if these semi-variograms were calculated on
          thousands of points, many are showing pure noise. Nevertheless, some
          dare fitting a model on these semi-variograms and derive conclusions
          and/or generate maps.

          My 2 cents contribution for the week ...

          Cheers,

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