0

I want to correlate two arrays (A and B) from a medical image. I expect a high correlation since they come from the same patient (acquired twice in the same session). 

[rho, p] = corr(A(:), B(:))

gives me rho = 0.8321 but p = 0.1255 so the correlation is not significant.

I have read that an approach could be a bootstrap analysis and did something like: 

rho_boot = bootstrp(1000,'corr',A,B)

resulting with a distribution of 1000 rho values.

The question is: can I consider mean(rho_boot(:)) my new rho value?
I have also read on mathworks that

(...)this evidence does not require any strong assumptions about the probability distribution of the correlation coefficient.

In fact, I have lost track of my p value.

StupidWolf
  • 45,075
  • 17
  • 40
  • 72
Inchan
  • 1
  • 3

1 Answers1

0

I believe your initial line of code is correct, I think your issue might be that you are not correlating what you want to be correlating. You are essentially making a comparison between each pixel, which means that if there is a shift in the images in any way the correlation will be off. You need to align them before you run this code, and you might also want to think about using the corr2 function instead.

Raha
  • 202
  • 1
  • 8
  • Thank you for your comment. Images have been coregistered before this correlation attempt and A and B are twp [1xN] arrays. – Inchan Jul 20 '18 at 16:43