Jump to content

  • Log in with Facebook Log in with Twitter Log in with Windows Live Log In with Google      Sign In   
  • Create Account

Submit your paper to J Biol Methods today!
- - - - -

Different p-values obtained for PERMDISP from the software Primer7 and the R pac


  • Please log in to reply
No replies to this topic

#1 Olli Laroche

Olli Laroche


  • Members
  • Pip
  • 1 posts

Posted 06 December 2016 - 04:46 PM

Using the same Bray-Curtis similarity matrice, I ran an PERMDISP test using the R package Vegan, and than ran the same test using the software Primer7. I was expecting to get exactly the same results but for an unknown reason (at least to me), I am getting different p-values for both tests. What is strange is that all other values are the same (e.g. degree of freedom for each group, number of permutation[999], f-values). Now I know that these p-values are based on permutations and that slight differences may occur but here I get very different outcomes... Is there anyone who could insight me on this great mystery? Cheers

Vegan -> PERMDISP: F-value = 5.449, p-value =  0.042

Primer7 -> PERMDISP: F-value = 5.449, p-value = 0.239


Home - About - Terms of Service - Privacy - Contact Us

©1999-2013 Protocol Online, All rights reserved.