+ Reply to Thread
Results 1 to 2 of 2

Thread: Permutation correlation with one non-normal variable

  1. #1
    Points: 658, Level: 13
    Level completed: 16%, Points required for next Level: 42

    Posts
    8
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Permutation correlation with one non-normal variable




    Hi,

    I am trying to assess the relationship between a relatively normally distributed variable (brain volume) and a strongly right-skewed behavioral measures, which cannot be transformed to normality. I assume a linear relationship between the two variables.

    My plan is to calculate the pearson correlation, and then permute one of the variables a number of times to get a significance value. Unfortunately I cannot find a lot of information on correlation permutation. Would this be a valid approach?

    Best,

    Niels

  2. #2
    Points: 658, Level: 13
    Level completed: 16%, Points required for next Level: 42

    Posts
    8
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Permutation correlation with one non-normal variable


    For anyone else with the same problem, the method I describe appears to be valid (Testing the Significance of a Correlation With Nonnormal Data: Comparison of Pearson, Spearman, Transformation, and Resampling Approaches; Bishara and Hittner, 2012)

+ Reply to Thread

           




Tags for this 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