R help - Nov 2005 - Query

Dear all,
 
My name is Guillermo I'm trying to write a short program to find all the
possible combination in fitting an ARIMA Model. My script is the
following:
 
n=rnorm(100)+5
Aux.M=matrix(NA,nrow=100,ncol=2)
L=1
for(i in 0:2)
{for(j in 0:2) {for(k in 0:2) 
 
Aux.M[L,2]=arima(n,order=c(i,j,k),include.mean=TRUE)$aic
 
x1=paste("AR=",i,sep=" ")
x2=paste("I=",j,sep=" ")
x3=paste("MA=",k,sep=" ")
x4=paste(x1,x2,sep=" ")
x5=paste(x4,x3,sep=" ")
 
Aux.M[L,1]=x5
L=L+1}}
 
After running in R, you will realize that the last for does not work. So
I have problem using three 'for command' at the same time, and I do not
know exactly how to solve the problem. Are there any more efficient
approach? (i.e. using a combination of while and for) Could somebody
help me?


This message has been scanned for viruses by TRENDMICRO,
an IESE technology affiliate company  and global leader in antivirus and content
security software.

	[[alternative HTML version deleted]]

On Wed, 9 Nov 2005, Armelini, Guillermo wrote:
> Dear all,
>
> My name is Guillermo I'm trying to write a short program to find all
the
> possible combination in fitting an ARIMA Model. My script is the
> following:
>
> n=rnorm(100)+5
> Aux.M=matrix(NA,nrow=100,ncol=2)
> L=1
> for(i in 0:2)
> {for(j in 0:2) {for(k in 0:2)
need { here
> Aux.M[L,2]=arima(n,order=c(i,j,k),include.mean=TRUE)$aic
>
> x1=paste("AR=",i,sep=" ")
> x2=paste("I=",j,sep=" ")
> x3=paste("MA=",k,sep=" ")
> x4=paste(x1,x2,sep=" ")
> x5=paste(x4,x3,sep=" ")
>
> Aux.M[L,1]=x5
> L=L+1}}
need another } here
> After running in R, you will realize that the last for does not work. So
It does, but you did not store the resutls from it as you probably 
intended.
> I have problem using three 'for command' at the same time, and I do
not
> know exactly how to solve the problem. Are there any more efficient
> approach? (i.e. using a combination of while and for) Could somebody
> help me?
You have forgotten the braces for the body of the inner for() loop.
Also, 27 combinations does not need 100 rows to store.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595