+ Reply to Thread
Results 1 to 2 of 2

Thread: Which Correlation is correct?

  1. #1
    Points: 1,482, Level: 21
    Level completed: 82%, Points required for next Level: 18

    Posts
    26
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Which Correlation is correct?




    Hi there, I'm having a bit of a problem with the last bit of analysis for my thesis.

    I would like to compare wave exposure of sites along the U.S. west coast against sea urchin spine repair rings.

    My hypothesis is that a site with high wave exposure causes lots of spine breakage. Whenever a spine is broken, a new ring forms, and they look like tree rings.

    So basically, my theory is higher wave variation means more spine rings.

    I have 11 sites, each with its own set of repair cycle data (75 points) and its own set of water level stdev's (~75).

    Is there anyway to compare these? I am using JMP and my advisor suggested I just take the average of each data set per site and use Kendall's tau ranking multivariate analysis. Is there a test like KT that doesn't use ranks, but instead uses raw data? Should I use a different method of correlation? I would like to keep the sites separate so that I can rank them after the analysis has been completed.

  2. #2
    Points: 1,482, Level: 21
    Level completed: 82%, Points required for next Level: 18

    Posts
    26
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Which Correlation is correct?


    Another way to think of it is this: If I took a box/whisker plot of wave exp per site and I wanted to compare it to a box/whisker plot of spine repair rings per site. Does that make sense? I think the problem with KT is that it assumes values are paired across rows.

+ 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