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

AI-GEOSTATS: Autologistic regression for post-fire forest study

Expand Messages
  • Agnes Wong
    Hi, I am working on a study characterizing post-fire island remnants and their fire boundaries. The study design is as follows: My study site consists of 9
    Message 1 of 2 , May 14 8:47 AM
    • 0 Attachment
      Hi,

      I am working on a study characterizing post-fire island remnants and their
      fire boundaries. The study design is as follows:

      My study site consists of 9 different island remnants. In each remnant, 2 -
      3 100m transects of contiguous 5m x 5m quadrats were placed across the fire
      edge (burned to unburned).
      Tree species, DBH, density, age, various environmental and topographical
      variables were sampled from each quadrat. I would like to test whether
      certain variables can best discriminate burned/unburned quadrats. There is
      spatial autocorrelation along the transect, between transects from the same
      remnant and between remnants that are near each other.
      I have tried regular GLM models for the entire dataset and for each
      transect. Unfortunately, the residuals are highly autocorrelated. Splus and
      R both have spatial linear modelling functions but none for logistic
      regression (that I know of). Are there any programs or packages that can do
      autologistic regression? I have thought of adding a location covariate but I
      only have fire edge long/lat for each transect therefore it would not
      directly deal with autocorrelation along the transect.

      Any input and suggestions would be greatly appreciated! Thanks in advance,

      Agnes

      ====================================
      Agnes Wong
      M.Sc. Candidate
      Environmental Biology and Ecology
      Dept. Biological Sciences
      Edmonton, AB
      agnesw@...
      ====================================


      --
      * 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
    • Nicholas Lewin-Koh
      Hi, If you look on statlib in the S archive there is code submitted by Jenifer Hoeting for Bayesian autologistic regression. Look at
      Message 2 of 2 , May 14 7:07 PM
      • 0 Attachment
        Hi,
        If you look on statlib in the S archive there is code submitted by Jenifer
        Hoeting for Bayesian autologistic regression. Look at
        http://lib.stat.cmu.edu/S/autologit.shar

        And Fred Huffer has some code he distributes at
        http://stat.fsu.edu/~huffer which computes MCMC approximations to the
        mle. You should look at Huffer and Wu, auto logistic regression for the
        distribution of plant species.

        Sounds like a neat project.


        Nicholas

        CH3
        |
        N Nicholas Lewin-Koh
        / \ Dept of Statistics
        N----C C==O Program in Ecology and Evolutionary Biology
        || || | Iowa State University
        || || | Ames, IA 50011
        CH C N--CH3 http://www.public.iastate.edu/~nlewin
        \ / \ / nlewin@...
        N C
        | || Currently
        CH3 O Graphics Lab
        School of Computing
        National University of Singapore
        The Real Part of Coffee kohnicho@...

        On Mon, 14 May 2001, Agnes Wong wrote:

        > Hi,
        >
        > I am working on a study characterizing post-fire island remnants and their
        > fire boundaries. The study design is as follows:
        >
        > My study site consists of 9 different island remnants. In each remnant, 2 -
        > 3 100m transects of contiguous 5m x 5m quadrats were placed across the fire
        > edge (burned to unburned).
        > Tree species, DBH, density, age, various environmental and topographical
        > variables were sampled from each quadrat. I would like to test whether
        > certain variables can best discriminate burned/unburned quadrats. There is
        > spatial autocorrelation along the transect, between transects from the same
        > remnant and between remnants that are near each other.
        > I have tried regular GLM models for the entire dataset and for each
        > transect. Unfortunately, the residuals are highly autocorrelated. Splus and
        > R both have spatial linear modelling functions but none for logistic
        > regression (that I know of). Are there any programs or packages that can do
        > autologistic regression? I have thought of adding a location covariate but I
        > only have fire edge long/lat for each transect therefore it would not
        > directly deal with autocorrelation along the transect.
        >
        > Any input and suggestions would be greatly appreciated! Thanks in advance,
        >
        > Agnes
        >
        > ====================================
        > Agnes Wong
        > M.Sc. Candidate
        > Environmental Biology and Ecology
        > Dept. Biological Sciences
        > Edmonton, AB
        > agnesw@...
        > ====================================
        >
        >
        > --
        > * 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
      Your message has been successfully submitted and would be delivered to recipients shortly.