[R] arma.predict?
Skanda Kallur; MEngg
s2112930 at student.rmit.edu.au
Fri May 16 21:24:29 CEST 2003
Professor, thanks for the reply, I am using Auto Regression Moving Average arma()(sorry it wasnt ARMA) which comes under tseries package to fit my data and I am intending to predict with arma fitted data but couldnt find a method to do it.
Interestingly, I found two packages at http://www.itp.phys.ethz.ch/econophysics/R/ which has packages called fbasic and fseries. fseries has arma.predict() but it threw some error, I wasnt able to install it. I would appreciate if you could have a look at it.
Regards
Skanda
-----Original Message-----
From: Prof Brian Ripley <ripley at stats.ox.ac.uk>
To: "Skanda Kallur; MEngg" <s2112930 at student.rmit.edu.au>
Date: Fri, 16 May 2003 19:29:37 +0100 (BST)
Subject: Re: [R] ARMA.predict?
On Sat, 17 May 2003, Skanda Kallur; MEngg wrote:
> Hi there,
>
> Does anyone know how to predict ARMA? It doesnât have either predict
> or forecast methods. I found couple of packages called fbasic and
> fseries at http://www.itp.phys.ethz.ch/econophysics/R/, which has
> âarma.predictâ in it, but it doesnât seem to be working. Any help
> in this regard would be appreciated. Thanks in advance.
Well, R comes with arima and arima0 functions, and both have predict
methods. What is ARMA and where did you get it from?
--
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
Skanda Kallur
"Prediction is very difficult, especially if it's about the future."
--Niels Bohr
More information about the R-help
mailing list