1. Forum
  2. Usenet
  3. SCI.STAT.CONSULT

  • RDA and linear dependence between variables

    From andrzejwuczynski@gmail.com@21:1/5 to All on Thu Oct 8 15:38:56 2015
    Hi,

    I would be most grateful for help regarding the redundancy analysis (RDA), since I must urgently answer the question to the journal editor. Sorry for my poor English and if the question emerges trivial.

    The problem concerns the occurrence of bird communities in relation to some environmental variables. I performed RDA in Canoco. In twelve plots there were 49 species with abundance data, against four continuous environmental variables. The editor noted
    that RDA assumes linear dependence of the response and explanatory variables, and asked whether I have verified that my data are linearly dependent.

    I'm not sure how to verify this dependence and if it's really necessary. I have reviewed several papers and did not found any good answer. Is that truth that each species should be treated a response variable? What about rare species? I did correlation
    matrix (in Statistica), most numerous species revealed a relationship close to linear, indeed, but not all of them. The log transformation does not help. Overall, I suppose that there may be a general error in the attempt, but I wonder where.

    Thanks for help

    Andrzej
    (Poland)

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From Rich Ulrich@21:1/5 to All on Mon Oct 12 12:50:55 2015
    On Thu, 8 Oct 2015 15:38:56 -0700 (PDT), andrzejwuczynski@gmail.com
    wrote:

    Hi,

    I would be most grateful for help regarding the redundancy analysis (RDA), since I must urgently answer the question to the journal editor. Sorry for my poor English and if the question emerges trivial.

    The problem concerns the occurrence of bird communities in relation to some environmental variables. I performed RDA in Canoco. In twelve plots there were 49 species with abundance data, against four continuous environmental variables. The editor noted
    that RDA assumes linear dependence of the response and explanatory variables, and asked whether I have verified that my data are linearly dependent.

    I'm not sure how to verify this dependence and if it's really necessary. I have reviewed several papers and did not found any good answer. Is that truth that each species should be treated a response variable? What about rare species? I did correlation
    matrix (in Statistica), most numerous species revealed a relationship close to linear, indeed, but not all of them. The log transformation does not help. Overall, I suppose that there may be a general error in the attempt, but I wonder where.

    Thanks for help

    Andrzej
    (Poland)

    Even when we were a busy group, I don't think that we
    had experts who were involved with ecological data.

    What I discovered while looking up Correspondence
    Analysis is a site that seems to build upon ecology, and
    which includes many relevant techniques - Oklahoma State
    University.

    http://ordination.okstate.edu/overview.htm

    That page has only a few comments on RDA, but maybe
    they will help directly or indirectly.

    --
    Rich Ulrich

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From andrzejwuczynski@gmail.com@21:1/5 to All on Wed Oct 14 01:51:18 2015
    W dniu poniedziałek, 12 października 2015 18:50:56 UTC+2 użytkownik Rich Ulrich napisał:
    On Thu, 8 Oct 2015 15:38:56 -0700 (PDT), andrzejw...@gmail.com
    wrote:

    Hi,

    I would be most grateful for help regarding the redundancy analysis (RDA), since I must urgently answer the question to the journal editor. Sorry for my poor English and if the question emerges trivial.

    The problem concerns the occurrence of bird communities in relation to some environmental variables. I performed RDA in Canoco. In twelve plots there were 49 species with abundance data, against four continuous environmental variables. The editor
    noted that RDA assumes linear dependence of the response and explanatory variables, and asked whether I have verified that my data are linearly dependent.

    I'm not sure how to verify this dependence and if it's really necessary. I have reviewed several papers and did not found any good answer. Is that truth that each species should be treated a response variable? What about rare species? I did
    correlation matrix (in Statistica), most numerous species revealed a relationship close to linear, indeed, but not all of them. The log transformation does not help. Overall, I suppose that there may be a general error in the attempt, but I wonder where.

    Thanks for help

    Andrzej
    (Poland)

    Even when we were a busy group, I don't think that we
    had experts who were involved with ecological data.

    What I discovered while looking up Correspondence
    Analysis is a site that seems to build upon ecology, and
    which includes many relevant techniques - Oklahoma State
    University.

    http://ordination.okstate.edu/overview.htm

    That page has only a few comments on RDA, but maybe
    they will help directly or indirectly.

    --
    Rich Ulrich

    Thank you for this hint. The Ordination Webpage is really interesting. Actually, I sent my post also to that list, but there was no response, unfortunately.

    Andrzej

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)