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.
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
"Prediction is very difficult, especially if it's about the future."
More information about the R-help