[R-sig-eco] procrustes() and protest() in vegan: any hints on the interpretation?
Gian Maria Niccolò Benucci
gian.benucci at gmail.com
Tue Oct 17 17:51:02 CEST 2017
Good morning r-sig-ecologists,
I have a question for you on how to have a correct interpretation of
protest() output. I have read the R documentation where it is reported that
a correlation-like statistics is computed from the symmetric Procrustes sum
of squares also called squared m12 = sqrt(1-ss). Based on my knowledge, the
smaller the residual sum of squares, the better your model fits your data.
In this context my question is: Do I need a "big" m12 to say that my two
ordination configuration were matching?
Below my protest() result:
>protest(X = fungi_NMDS_LSU, Y = fungi_NMDS_ITS, permutations = 999)
Procrustes Sum of Squares (m12 squared): 0.111
Correlation in a symmetric Procrustes rotation: 0.9429
Significance: 0.001
Permutation: free
Number of permutations: 999
Thank you for your help,
--
Gian
*----- Do not print this email unless you really need to. Save paper and
protect the environment! -----*
[[alternative HTML version deleted]]
More information about the R-sig-ecology
mailing list