Skip to content

Using multiple species data for gam

2 messages · Rajendra Mohan Panda

#
Dear All

I find it difficult to run VGAM and MARS for multi-response data. In both
the models, I get an error message "variable names are limited to 10000
bytes". Is this due to my big data structure or else ? For your kind
information, I have 1500 spp. on 434 site locations, and I want to see the
impact of environment on community structure. I have to analyse how the
Western Himalaya community behaviour differ from the Eastern Himalaya.

I have been struggling to accommodate my data for model fitting since long,
could you please give some insights on my idea and how can I tackle the
error for successful model run.

I always appreciate your valuable advise.


Best Regards
Rajendra M Panda
School of Water Resources
Indian Institute of Technology Kharagpur

On 18 February 2015 at 09:32, Rajendra Mohan panda <rmp.iit.kgp at gmail.com>
wrote:

  
  
#
I regret that the error message was due to my  erroneous data. However, I
face another error message in VGAM run i.e., object "eta" not found. Kindly
explain why this happens and possible solutions for this.

Thanks in advance

Best Regards
Rajendra M Panda
School of Water Resources
Indian Institute of Technology Kharagpur

---------- Forwarded message ----------
From: Rajendra Mohan Panda <rmp.iit.kgp at gmail.com>
Date: 2 September 2015 at 18:08
Subject: Re: [R-sig-eco] Using multiple species data for gam
To: r-sig-ecology at r-project.org


Dear All

I find it difficult to run VGAM and MARS for multi-response data. In both
the models, I get an error message "variable names are limited to 10000
bytes". Is this due to my big data structure or else ? For your kind
information, I have 1500 spp. on 434 site locations, and I want to see the
impact of environment on community structure. I have to analyse how the
Western Himalaya community behaviour differ from the Eastern Himalaya.

I have been struggling to accommodate my data for model fitting since long,
could you please give some insights on my idea and how can I tackle the
error for successful model run.

I always appreciate your valuable advise.


Best Regards
Rajendra M Panda
School of Water Resources
Indian Institute of Technology Kharagpur

On 18 February 2015 at 09:32, Rajendra Mohan panda <rmp.iit.kgp at gmail.com>
wrote: