[R-sig-eco] Using multiple species data for gam (Rajendra Mohan panda)

[David Warton]

Sorry for the slow response Chris.
The answer is yes you can do factor analysis on this sort of data, but if it is highly discrete (e.g. pres/abs, counts with lots of zeros, ...) then you need a discrete version of factor analysis.  Methods for this have been around in the social sciences for a while ("GLLAMM"), but in ecology there are now a couple of papers on this and a few groups working on this at the moment.  Steven Walker has been having a crack at this, with methods for pres/abs data towards the back of:
http://www.esajournals.org/doi/abs/10.1890/11-0886.1

Otso Ovaskainen presented on this topic at ISEC last year, he has been working up some cool-sounding software with Guillaume Blanchet but I don't know if it's out yet.

Then there is Francis Hui et al in press at MEE: 
http://onlinelibrary.wiley.com/doi/10.1111/2041-210X.12236/abstract
complete with a YouTube video
https://www.youtube.com/watch?v=vyMsgyytcUI
and R package "boral"

And plenty more too coming soon I should think...

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/





-----Original Message-----
From: Chris Howden [mailto:chris at trickysolutions.com.au] 
Sent: Thursday, 19 February 2015 10:35 AM
To: David Warton; r-sig-ecology at r-project.org
Subject: RE: [R-sig-eco] Using multiple species data for gam (Rajendra Mohan panda)

I wonder, has anyone tried using a factor analysis on the species prior to further analysis to remove the multicollinearity? It's a fairly common method outside of ecology. I think the interpretation would be that each factor represents a 'guild' of species (to borrow a term from the birders out there).

Chris Howden B.Sc. (Hons) GStat.
Founding Partner
Data Analysis, Modelling and Training
Evidence Based Strategy/Policy Development, IP Commercialisation and Innovation
(mobile) +61 (0) 410 689 945
(skype) chris.howden
chris at trickysolutions.com.au




Disclaimer: The information in this email and any attachments to it are confidential and may contain legally privileged information. If you are not the named or intended recipient, please delete this communication and contact us immediately. Please note you are not authorised to copy, use or disclose this communication or any attachments without our consent.
Although this email has been checked by anti-virus software, there is a risk that email messages may be corrupted or infected by viruses or other interferences. No responsibility is accepted for such interference. Unless expressly stated, the views of the writer are not those of the company.
Tricky Solutions always does our best to provide accurate forecasts and analyses based on the data supplied, however it is possible that some important predictors were not included in the data sent to us. Information provided by us should not be solely relied upon when making decisions and clients should use their own judgement.

-----Original Message-----
From: R-sig-ecology [mailto:r-sig-ecology-bounces at r-project.org] On Behalf Of David Warton
Sent: Thursday, 19 February 2015 9:37 AM
To: 'r-sig-ecology at r-project.org'
Subject: Re: [R-sig-eco] Using multiple species data for gam (Rajendra Mohan panda)

Hi Rajendra,
I would not advise deleting species to get around issue with species correlation, at least, not in most instances.  The species responses are typically the responses of interest that you are trying to model so you should not subset them to try and satisfy some assumption - the goal should always be trying to change your model to fit the data, not changing the data to fit the model.

As has been mentioned a few times before, the method to use to analyse your data really depends on the analysis goal.  The research question affects whether or not you need to worry about species correlation, and if so, how to deal with it.

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: Wed, 18 Feb 2015 09:32:56 +0530

From: Rajendra Mohan panda
<rmp.iit.kgp at gmail.com<mailto:rmp.iit.kgp at gmail.com>>

Cc: "r-sig-ecology at r-project.org<mailto:r-sig-ecology at r-project.org>"
<r-sig-ecology at r-project.org<mailto:r-sig-ecology at r-project.org>>

Subject: Re: [R-sig-eco] Using multiple species data for gam

Message-ID:


<CAGTzHJtEirz5vE5qoUSHieoazpFKnGGiGtZPc+PxLgvmcwP1Yw at mail.gmail.com<mailto
:CAGTzHJtEirz5vE5qoUSHieoazpFKnGGiGtZPc+PxLgvmcwP1Yw at mail.gmail.com>>

Content-Type: text/plain; charset="UTF-8"



Dear Prof David Warton



Thanks a lot for your nice introspection on my data. I appreciate your

valuable comments. I am also trying to explore gamm or VGAM to match its

suitability with data. Its fine. However, I am thinking to reduce my data

structure by removing some of the species showing interspecific

correlation. Honestly speaking I do not have thought of it. Can you please

give more insights regarding this (interspecies correlation). I am also

interested in studying species-environment relationship (not by CCA or RDA).



Your kind comments are highly appreciated.





	[[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