R: [R] Correction for first order autocorrelation in OLS residuals

[Vito Muggeo]

The Cochrane Orcutt is probably an outdated approach to deal with
autocorrelation
and it is rather easy to write code.

Why don't you use a direct likelihood-based approach?

For gaussian data see the arima() function in ts package, or the Jim
Lindsey's packages (for instance the gar() function in the repeated package
at
http://alpha.luc.ac.be/~lucp0753/rcode.html

Also for GLM you can have a look at the Thomas Lumley's weave package that
implements different standard error estimators
http://faculty.washington.edu/tlumley/weave.html

hope this helps you,
best,
vito

----- Original Message -----
From: Wayne Jones <JonesW at kssg.com>
To: <r-help at stat.math.ethz.ch>
Sent: Wednesday, November 19, 2003 11:36 AM
Subject: [R] Correction for first order autocorrelation in OLS residuals


> Hi there fellow R-users,
>
> Can anyone tell me if there exits an R package that deals with serial
> correlation in the residuals of an lm model.
> Perhaps, using the Cochrane Orcutt or Praise Wilson methods?
>
> Thanks,
>
> Wayne
>
>
> Dr Wayne R. Jones
> Senior Statistician / Research Analyst
> KSS Limited
> St James's Buildings
> 79 Oxford Street
> Manchester M1 6SS
> Tel: +44(0)161 609 4084
> Mob: +44(0)7810 523 713
>
>
>
>
> KSS Ltd
> Seventh Floor  St James's Buildings  79 Oxford Street  Manchester  M1 6SS
England
> Company Registration Number 2800886
> Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305
> mailto:kssg at kssg.com http://www.kssg.com
>
>
> The information in this Internet email is confidential and m...{{dropped}}
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help