I have two sets of pairs:

<distance, correlation>

where the correlation is the Pearson coefficient between two samples, and distance is their relative distance according to some measure.

For each value of distance, I usually have lots of values of correlation.

I want to test if the correlation in the first set is higher than the correlation in the second one.

What I want to test is if for any fixed distance, in general the correlations are higher in the first set; I would like to associate a pValue to this.

I have no idea on how to proceed, can you help?

  • 1
    $\begingroup$ Ideally, you would want to know the sizes of the samples used to compute each correlation--or, at a minimum, you would want to be sure those sizes were either (a) close to the same or (b) all very large. So: what do you know about the sample sizes? $\endgroup$ – whuber Feb 24 '16 at 13:19
  • 1
    $\begingroup$ Dear @whuber, each sample is a vector of approximately 200 dimensions. Also, all the samples have the same size. $\endgroup$ – Aslan986 Feb 24 '16 at 13:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.