Rainer M Krug
2006-Aug-30 10:27 UTC
[R] density() with from, to or cut and comparrison of density()
Hi
the function density() does normally integrate to one - I've checked it
and it works and I also read the previous threads.
But I realised that it does not integrate to one if I use from, to or cut.
My scenario: I simulated densities of a plants originating from an sseed
source at distance zero. Therefore the density of the plants will be
highest close to zero. Is there anything I can do to have this pattern?
If I use 'from' or 'cut', the resulting densities do not
integrate to
one which I need as I want to compare different density curves.
Ny second question is concerning the bandwidth. An I correct in saying
that if I want to compare different density estimates that the bandwidth
should be the same for all of them?
Thanks in advance for your help,
Rainer
--
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation
Biology (UCT)
Department of Conservation Ecology and Entomology
University of Stellenbosch
Matieland 7602
South Africa
Tel: +27 - (0)72 808 2975 (w)
Fax: +27 - (0)21 808 3304
Cell: +27 - (0)83 9479 042
email: RKrug at sun.ac.za
Rainer at krugs.de
Uwe Ligges
2006-Aug-30 11:01 UTC
[R] density() with from, to or cut and comparrison of density()
Rainer M Krug wrote:> Hi > > the function density() does normally integrate to one - I've checked it > and it works and I also read the previous threads. > But I realised that it does not integrate to one if I use from, to or cut. > > My scenario: I simulated densities of a plants originating from an sseed > source at distance zero. Therefore the density of the plants will be > highest close to zero. Is there anything I can do to have this pattern? > If I use 'from' or 'cut', the resulting densities do not integrate to > one which I need as I want to compare different density curves.The kernel chosen might be not the ideal one for such a restriction. If the density outside the "cut" range is extremely small, you might want to do a dirty transformation so that the values sum up to 1 again.> Ny second question is concerning the bandwidth. An I correct in saying > that if I want to compare different density estimates that the bandwidth > should be the same for all of them?Yes. Uwe Ligges> Thanks in advance for your help, > > Rainer >
Greg Snow
2006-Aug-30 16:08 UTC
[R] density() with from, to or cut and comparrison of density()
You may want to look at the logspline package, it uses a different
technique than density does, but it estimates densities and allows you
to tell the routine that there is a minimum value and that the density
does not extend beyond there.
Hope this helps,
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at intermountainmail.org
(801) 408-8111
-----Original Message-----
From: r-help-bounces at stat.math.ethz.ch
[mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Rainer M Krug
Sent: Wednesday, August 30, 2006 4:27 AM
To: R help list
Subject: [R] density() with from, to or cut and comparrison of density()
Hi
the function density() does normally integrate to one - I've checked it
and it works and I also read the previous threads.
But I realised that it does not integrate to one if I use from, to or
cut.
My scenario: I simulated densities of a plants originating from an sseed
source at distance zero. Therefore the density of the plants will be
highest close to zero. Is there anything I can do to have this pattern?
If I use 'from' or 'cut', the resulting densities do not
integrate to
one which I need as I want to compare different density curves.
Ny second question is concerning the bandwidth. An I correct in saying
that if I want to compare different density estimates that the bandwidth
should be the same for all of them?
Thanks in advance for your help,
Rainer
--
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation Biology (UCT)
Department of Conservation Ecology and Entomology University of
Stellenbosch Matieland 7602 South Africa
Tel: +27 - (0)72 808 2975 (w)
Fax: +27 - (0)21 808 3304
Cell: +27 - (0)83 9479 042
email: RKrug at sun.ac.za
Rainer at krugs.de
______________________________________________
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
and provide commented, minimal, self-contained, reproducible code.