R help - Apr 2012 - what is this warnings ?

i am running one script for many files,
Script file atttached:-
http://r.789695.n4.nabble.com/file/n4556770/AR_anarkali_aic.r
AR_anarkali_aic.r 
& warnings are given as below
what is meaning of these warnings?

Warning messages:
1: In optim(coef, err, gr = NULL, hessian = TRUE, ...) :
  one-diml optimization by Nelder-Mead is unreliable:
use "Brent" or optimize() directly

is there anything wrong with my code or my approach to calculate AIC values
?
how i know due to which function warnings is generated?
if i want to print warnings with file name then ...........?

--
View this message in context:
http://r.789695.n4.nabble.com/what-is-this-warnings-tp4556770p4556770.html
Sent from the R help mailing list archive at Nabble.com.

On 14-04-2012, at 08:33, sagarnikam123 wrote:
> i am running one script for many files,
> Script file atttached:-
> http://r.789695.n4.nabble.com/file/n4556770/AR_anarkali_aic.r
> AR_anarkali_aic.r 
> & warnings are given as below
> what is meaning of these warnings?
> 
> Warning messages:
> 1: In optim(coef, err, gr = NULL, hessian = TRUE, ...) :
>  one-diml optimization by Nelder-Mead is unreliable:
> use "Brent" or optimize() directly
> 
> is there anything wrong with my code or my approach to calculate AIC values
> ?
> how i know due to which function warnings is generated?
Well, isn't that obvious? In optim. It says so.

We don't have a datafile so we can't experiment.

According to the documentation of function arma in package tseries one can pass
additional arguments to optim.
Looking in the documentation for optim you can see that  there is a method
argument, which appears to have several options. Try arma(<your
arguments>, method="Brent").

You could easily have found this out on your own with:

- library(tseries)
- ?arma
- Click on link to optim

Berend