[R-sig-eco] mvabund SIMPER alternative

[David Warton]

Hi Vincent,
If you want to treat DNA and RNA jointly as your response you just need to stick them together into the same matrix.
e.g.
	dat =mvabund( cbind(DNA,RNA) )
If you are after a SIMPER-type analysis, make sure you set p.uni to "adjusted" or "unadjusted" rather than "none", so you can get univariate test statistics to use to rank OTU's.  Expect to get quite different results to SIMPER though - because SIMPER confounds effect size with error variance, the latter having a habit of varying considerably across responses and drowning out most of the signal.

All the best
David


 
David Warton
Professor and Australian Research Council Future Fellow
School of Mathematics and Statistics and the Evolution & Ecology Research Centre
The University of New South Wales NSW 2052 AUSTRALIA
phone (61)(2) 9385-7031
fax (61)(2) 9385-7123
 
http://www.eco-stats.unsw.edu.au/ecostats15.html




-----Original Message-----

Date: Tue, 2 Jun 2015 07:11:18 -0700 (MST)
From: carvin90 <vincentc at unis.no>
To: r-sig-ecology at r-project.org
Subject: Re: [R-sig-eco] mvabund SIMPER alternative
Message-ID: <1433254278212-7579464.post at n2.nabble.com>
Content-Type: text/plain; charset=us-ascii

Hi Mr. O'hara,

I am trying to see how to arrange the commands. I have an abundance matrix for DNA and an abundance matrix for RNA. 
In row are the stations, in column the species.
DNAb<-mvabund(as.matrix(DNA),row.names=DNA[,1],var.names=DNA[1,])
RNAb<-mvabund(as.matrix(RNA),row.names=RNA[,1],var.names=RNA[1,])

but then I am not sure how to integrate both objects in manyglm(...).

Thanks for your help!




--
View this message in context: http://r-sig-ecology.471788.n2.nabble.com/mvabund-SIMPER-alternative-tp7579461p7579464.html
Sent from the r-sig-ecology mailing list archive at Nabble.com.