[R] Errors using nlme's gls with autocorrelation

[Andrew Robinson]

You're running out of RAM.  Your options are

1) run code on a machine with more RAM

2) try the model on fewer observations

3) try a simpler model.

Andrew

On Fri, May 02, 2008 at 12:37:15PM -0700, zerfetzen wrote:
> 
> Hi,
> I am trying out a generalized least squares method of forecasting that
> corrects for autocorrelation.  I downloaded daily stock data from Yahoo
> Finance, and am trying to predict Close (n=7903).  I have learned to use
> date functions to extract indicator variables for Monday - Friday (and
> Friday is missing in the model to prevent it from becoming full rank).  When
> I run the following code...
> 
> > library(nlme)
> > MyModel <- gls(Close ~ Monday + Tuesday + Wednesday + Thursday,
> 	correlation=corARMA(p=2), data=MyData, method="ML")
> 
> ...I get the following error...
> 
> Error in corFactor.corARMA(object) : 
>   Calloc could not allocate (62457409 of 8) memory
> 
> ...Does anybody know what I'm doing wrong?  I appreciate any help.  Thanks.
> -- 
> View this message in context: http://www.nabble.com/Errors-using-nlme%27s-gls-with-autocorrelation-tp17026417p17026417.html
> Sent from the R help mailing list archive at Nabble.com.
> 
> ______________________________________________
> R-help at r-project.org 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.

-- 
Andrew Robinson  
Department of Mathematics and Statistics            Tel: +61-3-8344-6410
University of Melbourne, VIC 3010 Australia         Fax: +61-3-8344-4599
http://www.ms.unimelb.edu.au/~andrewpr
http://blogs.mbs.edu/fishing-in-the-bay/