[R-sig-eco] R-sig-ecology Digest, Vol 120, Issue 6

[David Warton]

Hi Alesandro,
You could try using the manyglm function in the mvabund package, and using size of univariate test statistics as a measure of variable importance.  This is a more reliable indicator than SIMPER and will work with any fixed effects design.
All the best
David


Professor David Warton
School of Mathematics and Statistics, Evolution & Ecology Research Centre, Centre for Ecosystem Science
UNSW Sydney
NSW 2052 AUSTRALIA
phone +61(2) 9385 7031
fax +61(2) 9385 7123
 
http://www.eco-stats.unsw.edu.au


-----Original Message-----
From: R-sig-ecology <r-sig-ecology-bounces at r-project.org> On Behalf Of r-sig-ecology-request at r-project.org
Sent: Saturday, 24 March 2018 10:00 PM
To: r-sig-ecology at r-project.org
Subject: R-sig-ecology Digest, Vol 120, Issue 6

Send R-sig-ecology mailing list submissions to
	r-sig-ecology at r-project.org

To subscribe or unsubscribe via the World Wide Web, visit
	https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
or, via email, send a message with subject or body 'help' to
	r-sig-ecology-request at r-project.org

You can reach the person managing the list at
	r-sig-ecology-owner at r-project.org

When replying, please edit your Subject line so it is more specific than "Re: Contents of R-sig-ecology digest..."


Today's Topics:

   1. Good alternative to SIMPER analysis for continuous variables?
      (Alessandro Manfrin)

----------------------------------------------------------------------

Message: 1
Date: Sat, 24 Mar 2018 06:19:42 +0100
From: Alessandro Manfrin <manfrin at igb-berlin.de>
To: r-sig-ecology at r-project.org <r-sig-ecology at r-project.org>
Subject: [R-sig-eco] Good alternative to SIMPER analysis for
	continuous variables?
Message-ID:
	<kcim.5ab5dfee.70e0.67e8468773debee3 at ucsmail01.ad.igb-berlin.de>
Content-Type: text/plain; charset="utf-8"

Dear all,
   I am conducting an analysis in which I have river sites restored and unrestored. Also, these sites are located over different altitudes, latitudes (continuous variables) and in different fish zones (categorical variable).

I used ADONIS (diss calculated with Bray Curtis) to assess differences in fish trait composition between restored and unrestored sites including also the interaction with both categorical and continuous variables:
Adonis.mod<-diss~Restoration*altitude+Restoration*latitudes+Restoration*fish
zones, strata=rivers

Now I would like to use SIMPER analysis to see which traits are responsable for the difference observed in Restoration*fish zones (categorical variable).

What can I use to understand which are the traits that are resonsable for difference in Restoration*altitude as SIMPER cannot be used for continuous variables?

Maybe stupidely I thought to do this: perform RDA (eclidean distance) on the delta values (Rest-Unrestored) and include the significant continuous variable from the ADONIS (i.e. altitude) in the rda analysis and then check visually which are the "species" of traits that are responding to the vector "altitude". Besideds the fact if it makes sense or not to do that, the other doubt that I have with RDA is related to the "random structure=river" for which I would like the rda to account the fact that I collected samples from different rivers in Germany (for which I believe I kind of considered in the Adonis with the function "strata=river"

Please tell me if I am wrong and if yes f you have some good suggestions.

Best regards

Alessandro




Dr. Alessandro Manfrin

University of Applied Sciences Trier, Umwelt Campus Birkenfeld/ University of Duisburg-Essen, Faculty of Biology

Working place:
Department of Aquatic Ecology
Room S05 T03 B02
Universitätsstr. 5
45141 Essen (DE)
Tel.: +49 (0)201/183-3113
Fax: +49 (0)201/183-2179







 

	[[alternative HTML version deleted]]




------------------------------

Subject: Digest Footer

_______________________________________________
R-sig-ecology mailing list
R-sig-ecology at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology


------------------------------

End of R-sig-ecology Digest, Vol 120, Issue 6
*********************************************