[R-sig-eco] Testing the difference between fractions in RDA

Gavin Simpson gavin.simpson at ucl.ac.uk
Fri Jul 9 12:32:51 CEST 2010


On Mon, 2010-07-05 at 11:59 +0800, Qi Li wrote:
> Hi,
> 
> A boot-strap method was proposed by Peres-Neto et al. (2006, Ecology)
> to test the difference between fractions in RDA, while they supplied a
> matlab code. Does the "vegan" package contain this kind of analysis to
> test the difference and estimate the confidence intervals on the R^2
> statistic?

If you mean the section from p2620-2622 in that paper, then no, that
bootstrap procedure is not implemented in vegan. The variance
partitioning part is (in function varpart) but it itself does not do any
testing of or generate confidence intervals on the R^2 components
returned. Looking at the paper it shouldn't be too hard to implement
given all the work that Jari has put into providing various methods for
cca (rda) objects but it is not something I currently have time to work
on.

If you fancy a stab at coding this up, be careful with computing the
coefficient matrices B_X and B_W as you probably don't want to be
computing the inverse of X'X directly. If you do give this a try but
want some help, try the vegan forum on R-Forge

https://r-forge.r-project.org/forum/forum.php?forum_id=194&group_id=68

where we can give further advice etc.

HTH

G

> 
> Best regards,
> 
> Qi Li
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology

-- 
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
 Dr. Gavin Simpson             [t] +44 (0)20 7679 0522
 ECRC, UCL Geography,          [f] +44 (0)20 7679 0565
 Pearson Building,             [e] gavin.simpsonATNOSPAMucl.ac.uk
 Gower Street, London          [w] http://www.ucl.ac.uk/~ucfagls/
 UK. WC1E 6BT.                 [w] http://www.freshwaters.org.uk
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%



More information about the R-sig-ecology mailing list