[R-sig-Geo] Fwd: help in CompRandFld package

[Edzer Pebesma]

Resending your email to the list twice a day is not a good style; please
assume that people read your email, or ignore it, but don't need to
receive it twice.

In this case, if reading the package documentation and relevant
literature does not help you, you might want to contact the package
authors. They may not be on this list.

On 05/01/2012 03:28 PM, Saman Monfared wrote:
> ---------- Forwarded message ----------
> From: Saman Monfared <samanmonfared1 at gmail.com>
> Date: Tue, 1 May 2012 12:31:30 +0430
> Subject: help in CompRandFld package
> To: r-sig-geo <r-sig-geo at r-project.org>
> 
> Dear All.
> I Try to use CompRandFld package for Spatio-temporal modeling of Irish
> wind data.
> I write Irish wind data in txt format. I calculate times in days
> ((year*365)+(month*30)+day)
> and saved in a coloumn with name times. I want fit a spatio-temporal
> covariance  like gneiting
> model.
> 
> A part of My program is :
> 
> 
> rm(list=ls())
> library(CompRandFld)
> library(RandomFields)
> dd<-read.table("wind.txt",header=T)
> names(dd)
> x <- dd$x
> y <- dd$y
> mean <- mean(dd$values)
> sill <- 1
> nugget <- 0
> scale <- 3
> set.seed(331)
> # Define the temporal sequence:
> times <- seq(1,10,1)
> # Simulation of a spatio-temporal Gaussian random field:
> data <- RFsim(x, y, times, corrmodel="gneiting",
> param=list(mean=mean,scale_s=3,scale_t=3,sill=sill,
> nugget=0,power_s=1,power_t=1,sep=0.2))$data
> ************************************************
> Error in chol.default(varcov) :
>   the leading minor of order 11 is not positive definite.
> 
> Please help me.
> 
> 

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763  http://ifgi.uni-muenster.de
http://www.52north.org/geostatistics      e.pebesma at wwu.de