Re: kud LSCV, h-ref, h-adj problems...

In un messaggio del Friday 23 December 2011, dr. VM Giacalone ha scritto:
> Hi everybody,
> I’m using qgis1.7.3 and the R-adehabitat package to evaluate the home range
> of my fish in a marine protected area. Well, I’m interested in comparing
> the different KUD… LSCV, h-adj, h-ref, but when I launch the application,
> I can get data about MCP and kud h-ref only, with the following message: R
> message (kernel LSCV): no subset converged, no output.
>  
> I have lots of FIX with the same coordinates due to the proximity of fish
> shelter to a receiver location. Arcview3 with animal movement routine is
> able to calculate LSCV kud while Arcgis9 and HRT routine seems to have the
> same “problem” of QGis. 
> My pc setup is winXP sp3, qgis1.7.3, R2.11.1.
>  
> Thanks in advance or your help and merry Christmas!
>  
> Max
>  

LSCV h calculations sometimes does not converge.
It's an old and well-known "property", already sorted out (it depends on the 
nature of the algorithm used to do least-squares...), and AFAIK no solution is 
possible.

Hooge's Animal Movement uses a sort of 'dirty trick': when LSCV is not 
converging, it goes back to fixed h calculations and gives back that (which is 
not what you intended, and - worse - you are not aware of that substitution).

Adehabitat is 'honest' in that warns you that LSCV did not converge.

If it can help, here's the R code I routinely use to calculate homeranges.

BTW: if you have several "identical" locations, as a rule of thumb there are two 
approaches: 
1) that location is a "den" or something behaviourally equivalent, e.g. a 
resting site, and in your experimental design is not part of the home range -> 
drop out all those locations
2) those points tend to accumulate around some location that actually is a 
center of activity (say, a foraging site), and they are part of the home range -
> have a look at the jitter() function ;)

Hope this Helps...

-- 
What makes the universe so hard to comprehend is that there's nothing
to compare it with.
 ----------------------------------------------------------
Damiano G. Preatoni, PhD

Unità di Analisi e Gestione delle Risorse Ambientali
  - Guido Tosi Research Group
Dipartimento di Scienze Teoriche e Applicate
Università degli Studi dell'Insubria
Via J.H. Dunant, 3 - 21100 Varese (ITALY)

tel +39 0332421538 fax +39 0332421446
http://biocenosi.dipbsf.uninsubria.it/
ICQ: 78690321 jabber: prea@... skype: prea.net
-----------------------------------------------------------
Please consider the environment before printing this email
Please do not send attachments in proprietary formats
http://www.gnu.org/philosophy/no-word-attachments.html
Use the UNI CEI Standard ISO/IEC 26300:2006
-----------------------------------------------------------
O< stop html mail - http://www.asciiribbon.org

_______________________________________________
AniMov mailing list
AniMov@...
http://lists.faunalia.it/cgi-bin/mailman/listinfo/animov