[R] about"Riply's K function"and "envelope"

[Roger Bivand]

On Mon, 27 Feb 2006, zhang jian wrote:

> I have tried the package"spatial" and "splance".But it is not good.

You are not correct. All three packages, spatial, splancs, and spatstat
can be used, and, for the same bounding window, will give the same
results. Your complain that spatstat has difficulties computing simulation
envelopes for 2000 points (in your fourth appeal for help) also seems
unlikely. My impression is that you are not following advice given, and
are trying to simulate with an unnecessarily large number of replications,
and very likely for far too many distance bins.

Please simplify your task to something that you can make work. In each of
the three packages, calculating khat and computing simulation envelopes is
just a couple of lines, so try to get them right on a small data set that
you understand. Following the examples in the package will be a good 
start.

Once you have made it work on a small subset of your data following the 
examples in the packages, you can scale up to your full data sets.

> I think there are some questions when I run the programs.
> I attach a part of data. can you help me try to do it? And attach a simple
> program to me.
> my plot is square, 500m*500m.
> > PIKO[1:10,]
>      code species  dbh     x     y   tag status branch
> 92  10142    PIKO 38.9  6.05 12.81 10165  alive      0
> 109 10213    PIKO 41.0  6.71 26.21 10202  alive      0
> 135 10222    PIKO 48.3 18.98 21.28 10214  alive      0
> 146 10223    PIKO 47.0 19.45 22.83 10224  alive      0
> 147 10223    PIKO 20.0 19.74 28.65 10225  alive      0
> 151 10223    PIKO 23.3 17.03 28.88 10229  alive      0
> 152 10223    PIKO 33.5 16.94 27.25 10230  alive      0
> 176 10232    PIKO 43.5 19.20 30.88 10248  alive      0
> 181 10233    PIKO 39.0 18.10 35.60 10252  alive      0
> 212 10243    PIKO 71.2  6.94 37.27 10281  alive      0
> 
> "x,y" are coordinations. I want to use them to do Ripley's K analysis.
> thank you very much!
> Help me!
>                                           jian zhang
> 
> On 2/27/06, Sundar Dorai-Raj <sundar.dorai-raj at pdf.com> wrote:
> >
> >
> >
> > zhang jian wrote:
> > > hi!
> > > I did Riply's K function and envelope in the package "SPATSTAT". When
> > the
> > > species number is less, it can work well and it is quickly. But when the
> > > species number is more(example:2000), it told me"memory limit". So I
> > change
> > > "memory limit". But the speed is very slow. I took 13 hours to run the
> > > programe.
> > > Perhaps there are other methods that can do it. Or just change some
> > > parsmeters.
> > > who can help me?
> > > Thank you!
> > >                                                                Jian
> > Zhang
> > >
> >
> > I don't have an example, but have you looked at ?Kenvl in the spatial
> > package?
> >
> > HTH,
> >
> > --sundar
> >
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
> 

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no