It depends on what he wants: For certain circumstances, persp on the
output of interp or loess is appropriate (Venables and Ripley 2002,
Modern Applied Statistics with S, 4th ed., p. 76).
hope this helps. spencer graves
Uwe Ligges wrote:
Mario Alberto Cozzuol wrote:
Hi,
I am doing my way on R, with much experimenting. So, I am trying to plot a 3d
graphic ussing "persp" and entering a data set (attached) of UTM coordinates
as x,y and a pH values as z. However when I try an error message comes out
telling that increasing x and y values are expected. Jus ordering the first
vector does not help, and, of course, order the first two independently makes
no sense since they are geographic coordinates. So, what I am doing wrong?
Thank you all very much for the help,
So you are not going to plot a surface, but "just" a set of points? In
that case persp() is inadequate. For example you can use cloud() in
package lattice, scatterplot3d() in package "scatterplot3d", the
packages djmrgl and rgl, or xgobi or ggobi as external software.
Uwe Ligges
Mario
--
Dr. Mario A. Cozzuol
Laborat�rio de Biologia Evolutiva
Universidade Federal de Rond�nia
BR 364, Km 9,5
78900-000 Porto Velho, RO
Brasil
Tel./Fax 55 69 217-8593
E-mail [EMAIL PROTECTED]
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
