[R] permutation analysis with randomly chosen subsets of a matrix

[Zoppoli, Gabriele (NIH/NCI) [G]]

Hello,

here is the problem:

I want to demonstrate that, on average, the Pearson's correlations of a specified subset of genes from a huge list (>18,000 columns) are higher than any randomly chosen subset of that list. I would therefore like to do a number of tests between that specified subset and randomly chosen ones from the "mother" list.

How could I do that? What would be an appropriate statistical test?

Thank you for your help! 


Gabriele Zoppoli, MD
Ph.D. Fellow, Experimental and Clinical Oncology and Hematology, University of Genova, Genova, Italy
Guest Researcher, LMP, NCI, NIH, Bethesda MD

Work: 301-451-8575
Mobile: 301-204-5642
Email: zoppolig at mail.nih.gov