[R] Procrustes

[Tara Dirilgen]

Hi again,

Just to clarify my question from previous email...

Example script:
A <- data[, c(1,2,3,4)]
B <- data[, c(5,6,7,8)]
library(vegan)
vare.proc <- procrustes(A,B, scale=FALSE, symmetric=FALSE)
vare.proc
summary(vare.proc)
plot(vare.proc)
#plot(vare.proc, kind=2)
residuals(vare.proc)
protest(A,B, scores = "sites", permutations = 999)


Data A and B are case scores from PCA's.

*Question*
Protest output-  'Correlation in a symmetric Procrustes rotation' comes out
as 1 for each different data I input. This does not seem correct as the
graphical output suggests otherwise as well the raw case scores show
that there is not a systematic relationship between the two series of data.
I am wondering what the reason for this is.

Thanks & kind regards,

Tara

On 19 February 2015 at 16:43, Tara Dirilgen <tara.dirilgen at ucdconnect.ie>
wrote:

> I have been using R to calculate the significance of Procrustes
> correlations. With one series of data, where there are five cases, the
> value returned for the correlation coefficient is one although there are
> differences as shown by the procrustes error graph. Is there a statistical
> reason for this? Similarly, when we look at the cas scores there is not a
> systematic relationship between the two series of data.
>
> Thanks
>
> Tara
>
> --
> Tara Dirilgen
> School of Biology & Environmental Science
> Science Center West
> University College Dublin
> Belfield, Dublin 4
> IRELAND
> tara.dirilgen at ucdconnect.ie
>



-- 
Tara Dirilgen
School of Biology & Environmental Science
Science Center West
University College Dublin
Belfield, Dublin 4
IRELAND
tara.dirilgen at ucdconnect.ie

	[[alternative HTML version deleted]]