+ Reply to Thread
Results 1 to 3 of 3

Thread: Clustering sites to compare with cluster of species similarity (dendrogram?)

  1. #1
    Points: 23, Level: 1
    Level completed: 45%, Points required for next Level: 27

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Clustering sites to compare with cluster of species similarity (dendrogram?)




    Hi,

    I hope someone can help me here. I kind of have something specific in mind to analyze parts of my data, but I am not sure how to get there. I analyzed the fauna at several sites of a river. Now I would like to

    1) cluster the sites (put "more similar" sites closer together than others) according to several variables that I measured (e.g. morphology [width, depth], %/type of vegetation in and along water, maybe water chemistry)

    2) compare this cluster with a cluster of those sites according to species similarity. This one I think I know how to do - e.g. with Soerensen-distance

    I don't know how I could cluster the sites according to my other variables besides species. I don't want one cluster for vegetation, one for morphology etc., I would like to have one cluster combining all of them. Is that even possible? ^^; Comparison between both clusters is supposed to happen visually showing two dendrograms. That way I could say that according to "cluster x" site 1 and 2 are very similar, though "cluster y" shows me that they are completely dissimilar according to species recorded. Sort of like that. It would be generally nice to be able to show similarities in sites (over several parameters).

    Hope this is understandable.

    Best would be if I could do it in R. But any suggestion is welcome, I would have to see how to get my hands on whichever program then.

    Cheers,
    Aquaziell

  2. #2
    TS Contributor
    Points: 6,789, Level: 54
    Level completed: 20%, Points required for next Level: 161
    terzi's Avatar
    Location
    Mexico City, Mexico
    Posts
    420
    Thanks
    10
    Thanked 34 Times in 33 Posts

    Re: Clustering sites to compare with cluster of species similarity (dendrogram?)

    Hi Aquaziell,

    Hierarchical clustering algorithms may be useful to generate the groups. If you have a diverse,mixed type of variables, Gower's dissimilarity measure may be of use.

    Good luck
    Statisticians are engaged in an exhausting but exhilarating struggle with the biggest challenge that philosophy makes to science: how do we translate information into knowledge

  3. #3
    Points: 23, Level: 1
    Level completed: 45%, Points required for next Level: 27

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Clustering sites to compare with cluster of species similarity (dendrogram?)


    Hi terzi,

    thank you very much!

    Aquaziell

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats