headers
Isaac Brito Morales | 1 Jul 18:25
Picon
Favicon

Spatial Statistics


Dear list members,

I'm working in a spatial analysis field, and i built a code for estimated the nearest distance among two
circles. The problem is that this circles have an area and "the real distance" is among the boundaries of
this circles. As you can see in the code below, i saw that i corrected this problem but in the last part, and i
have to do it in the first part. 

Thank you very much in advance.
Best,

Isaac

  ####### Nearest Neighbours ##########

  NearestNeighbours<-function(data,pos){
  require(fields)

  d<-data[pos,]
  posiciones<-d[,1:2]
  area<-data[,3]
  D<-rdist(posiciones,posiciones)
  diag(D)<-NA

  out<-NULL

  for(i in 1:nrow(D)){
  index<-which.min(D[i,])[1]
  nn<-d[index,1:2]
  radio1<-sqrt(d[index,3]/pi)
(Continue reading)

Permalink | Reply | 0 comments |
headers
Manuel Spínola | 2 Jul 22:10
Picon
Favicon

Statistics applied to Geography using R

Dear list members,

Do you know any references for statistics applied to geography that are 
in some way related to R?
I think it will be ok also for references that do not use R but it will 
be easy to use through R.
Thank you very much in advance.
Best,

Manuel Spínola

--

-- 
Manuel Spínola, Ph.D.
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
mspinola@...
mspinola10@...
Teléfono: (506) 2277-3598
Fax: (506) 2237-7036
Permalink | Reply | 2 comments |
headers
Cord Melton | 3 Jul 00:10
Favicon

Re: Statistics applied to Geography using R

At the risk of stating the obvious, I believe there's another mailing list
for such things that might get you better results:

https://stat.ethz.ch/mailman/listinfo/r-sig-geo
gmane interface: http://news.gmane.org/gmane.comp.lang.r.geo

On Thu, Jul 2, 2009 at 3:10 PM, Manuel Spínola <mspinola@...> wrote:

> Dear list members,
>
> Do you know any references for statistics applied to geography that are in
> some way related to R?
> I think it will be ok also for references that do not use R but it will be
> easy to use through R.
> Thank you very much in advance.
> Best,
>
> Manuel Spínola
>
> --
> Manuel Spínola, Ph.D.
> Instituto Internacional en Conservación y Manejo de Vida Silvestre
> Universidad Nacional
> Apartado 1350-3000
> Heredia
> COSTA RICA
> mspinola@...
> mspinola10@...
> Teléfono: (506) 2277-3598
> Fax: (506) 2237-7036
(Continue reading)

Permalink | Reply | 1 comment |
headers
Gavin Simpson | 3 Jul 01:37
Picon
Picon
Favicon

Re: Statistics applied to Geography using R

On Thu, 2009-07-02 at 17:10 -0500, Cord Melton wrote:
> At the risk of stating the obvious, I believe there's another mailing list
> for such things that might get you better results:
> 
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> gmane interface: http://news.gmane.org/gmane.comp.lang.r.geo

Contrary to popular belief, the study of Geography does not start and
end with maps, mapping or other such geo-locational data. The "science"
has moved on a little since the first (UK) Geography Department was
established some 180+ years ago....

G (A "geographer")

> 
> On Thu, Jul 2, 2009 at 3:10 PM, Manuel Spnola <mspinola@...> wrote:
> 
> > Dear list members,
> >
> > Do you know any references for statistics applied to geography that are in
> > some way related to R?
> > I think it will be ok also for references that do not use R but it will be
> > easy to use through R.
> > Thank you very much in advance.
> > Best,
> >
> > Manuel Spnola
> >
> > --
> > Manuel Spnola, Ph.D.
(Continue reading)

Permalink | Reply | 0 comments |
headers
Manuel Spínola | 4 Jul 13:37
Picon
Gravatar

Re: Statistics applied to Geography using R

Thank you very much Dr. Oksanen,

I was thinking in a very general sense because the idea is to cover the 
topic for undergraduate course, covering from regression to cluster 
analysis and also some geostatistics.  The idea is to show those 
analysis using geographic data.
Best,

Manuel

Jari Oksanen wrote:
> Manuel, It would be very useful to know what you mean with 'geography'. Ideological and cultural aspects
in regional transformation or periglacial processes? Geography is one of the most variable fields of
science, and sometimes people have trouble in defining what is geography (indeed, I had a book exam on that
subject when studying geography). One thing is clear: geostatistics is not equal to geography.
Biogeography and palaeoecology may be - depends who you ask. A bit more specific question could perhaps
get informative answers.
>
> Cheers, Jari Oksanen 
> -----Original Message-----
> From: Manuel Spínola
> Sent:  02.07.2009, 23:17 
> To: r-sig-ecology <at> r-project.org
> Subject: [R-sig-eco] Statistics applied to  Geography using R
>
> Dear list members,
>
> Do you know any references for statistics applied to geography that are 
> in some way related to R?
> I think it will be ok also for references that do not use R but it will
(Continue reading)

Permalink | Reply | 1 comment |
headers
Paulo Inácio de Kn?ßISO-8859-1?Q?egt López de Prado | 4 Jul 16:31
Picon
Picon

Neighbor sampling is random?

Dear r-eco-list users,

This is not an R-question, but a statistical one, but maybe somebody can help.

I had read that to set random points over an area and picking the nearest
plant is not random sample, but I could not recover this article.

Is that correct? Could you provide some basic reference?

Thanks a lot

Paulo

--
Paulo Inácio de Knegt López de Prado
Depto. de Ecologia - Instituto de Biociências - USP
Rua do Matão, travessa 14, nº 321
Cid. Universitária, São Paulo - SP
CEP 05508-900
11-30917599 (sala)
11-30917600 (Secretaria)
Permalink | Reply | 3 comments |
headers
Salvador Sánchez-Colón | 4 Jul 18:10
Picon

Re: Neighbor sampling is random?

Quite right, she did in there. Just for Paulo's file in case he does not 
manage to find that old (but most enlightening) book: That sampling 
scheme leads to an over-representation of isolated plants; that is, 
those plants have a higher probability of being included in the sample.

Muito pracer,

Salvador

Salvador Sánchez-Colón,
Consultoría Ambiental y Estadística,
Cerrada de Cortés 43,
Colonia Campestre Tlacopac,
San Ángel,
01049 México, DF
tel: (+52-55)5662-4644
mobile: (+52-1-55)3200-8559
e-mail: salvadorsanchezcolon@...

Jari Oksanen escribió:
> E. C. Pielou may be one of the first who wrote about this. Check her book 'Mathematical ecology' (J. Wiley,
1977). 
> 
> Best wishes, Jari Oksanen
> -----Original Message-----
> From: Paulo Inácio de Knegt López de Prado
> Sent:  04.07.2009, 17:35 
> To: r-sig-ecology@...
> Subject: [R-sig-eco] Neighbor sampling is random?
>
(Continue reading)

Permalink | Reply | 0 comments |
headers
Kingsford Jones | 4 Jul 18:55
Picon

Re: Neighbor sampling is random?

This may help a bit with intuition.  Think about randomly picking a
spot in the box below and then choosing the nearest neighbor.  What's
the inclusion probability for 1?  What about 6?  Clearly not a simple
random sample...

 -----------
|123       |
|456       |
|           |
|           |
 -----------

hth,

Kingsford Jones

2009/7/4 Paulo Inácio de Knegt López de Prado <prado@...>:
> Dear r-eco-list users,
>
> This is not an R-question, but a statistical one, but maybe somebody can help.
>
> I had read that to set random points over an area and picking the nearest
> plant is not random sample, but I could not recover this article.
>
> Is that correct? Could you provide some basic reference?
>
> Thanks a lot
>
> Paulo
>
(Continue reading)

Permalink | Reply | 0 comments |
headers
Fred Takahashi | 4 Jul 22:25
Picon

Re: R-sig-ecology Digest, Vol 14, Issue 3

Dear Thomas

Sorry about the delay of my reply. I had an unexpected long field work
in the last months. But in the last two weeks, I was working on FME
package and finally I reached good results. Your team had done a very
nice work on this package, bring really flexible functions. One of the
interest points of the package are the several options of methods for
fitting the equations (minimization algorithms). In fact, in all my
tests, the “Pseudo-random Search Optimisation Algorithm of Price”
reached equivalent results to Levenberg-Marquardt algorithm, but
releasing us of search good starting values (and the dangers of local
minimums).

Thank you very much for your help.

Fred Takahashi

PhD student
Universidade de Brasilia - Brazil

2009/5/4  <r-sig-ecology-request@...>:
> Send R-sig-ecology mailing list submissions to
>        r-sig-ecology@...
>
> 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@...
>
> You can reach the person managing the list at
(Continue reading)

Permalink | Reply | 1 comment |
headers
Paulo Prado | 5 Jul 17:42
Picon
Picon

Re: Neighbor sampling is random?


Thank very much to all.

Kingsford's comment remind me that a general way to demonstrate this is
trough a Dirichlet tessellation.

Best

Paulo

Paulo Prado wrote:
> 
> Dear r-eco-list users,
> 
> This is not an R-question, but a statistical one, but maybe somebody can
> help.
> 
> I had read that to set random points over an area and picking the nearest
> plant is not random sample, but I could not recover this article.
> 
> Is that correct? Could you provide some basic reference?
> 
> Thanks a lot
> 
> Paulo
> 
> --
> Paulo Inácio de Knegt López de Prado
> Depto. de Ecologia - Instituto de Biociências - USP
> Rua do Matão, travessa 14, nº 321
(Continue reading)

Permalink | Reply | 1 comment |

Gmane