residuals in RDA, and test for spatial autocorrelation

Hi Tracy,

You can try this:

require (vegan)

data(mite)
data(mite.env)
data(mite.xy)

mod<- rda (mite~., data=mite.env)
res<-residuals(mod)

require (spacemakeR)

vario<-variogmultiv(res, mite.xy)
plot(vario$d, vario$var, ty='b',pch=20,xlab="Distance", ylab="C(distance)")


But, I'm not sure. Maybe to implement spatial variables in the model through
spatial eigenfuncion analysis (e.g., db-MEM, MEM) also could be very useful.

Hope this helps.

Best



--
View this message in context: http://r-sig-ecology.471788.n2.nabble.com/residuals-in-RDA-and-test-for-spatial-autocorrelation-tp7578814p7578818.html
Sent from the r-sig-ecology mailing list archive at Nabble.com.

Dear Tracy,

You can see if Helene Wagner's mso() in function in vegan satisfies your needs for analysing spatial dependence. Reference and further description in ?mso.

Cheers, Jari Oksanen

Hello List,

I have two questions.


1.)    How do I generate a matrix of residuals in RDA (I am using rda() in vegan)?

2.)    How can I test for spatial dependence (spatial autocorrelation) in the response matrix of a multivariate analysis (RDA in my case)?  I have read that you can look at the trace of the variogram matrix as a multivariate alternative to Moran's I, but I don't know the details of how to make this test happen using R.

Thanks for any help!

Tracy


	[[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