**From:** Keith Campbell (*keithc@rotellacapital.com*)

**Date:** Tue 25 May 2004 - 07:15:16 EST

**Next message:**Dirk Eddelbuettel: "Re: [R] RQuantlib ?Windows Binary?"**Previous message:**Paul Bivand: "Re: [R] Tramo-seats"

Message-id: <053B1BC31740FE46B5EC8369B953F5F7397F8D@XOC1VEXC002.xoc1.com>

To whom it may concern:

I am trying to better understand the functionality of 'R' when making

arima predictions to avoid any "Black Box" disadvantages.

I'm fitting a seasonal arima model using the following command (having

already loaded 'stat' package).

arimaSeason <-

arima(Data,order=c(1,0,1),seasonal=list(order=c(1,0,1),period=12))

I can then generate subsequent predictions using the 'predict' function.

However, I can't seem to duplicate these predictions in a separate

program using the model coefficients. From duplicating simpler models,

I understand the input variables are adjusted by the intercept term.

(e.g. for an arima(1,0,0) the prediction equation is y(t) = beta1 * (

y(t-1) - beta0 ) + beta0 ....where beta0 is the intercept)

Currently, I've expected the prediction to follow the equation below:

y(t) = beta0 + [beta1*( y(t-1) - beta0 )] + [beta2 * epsilon(t-1)]

+ [beta3 * (y(t-12) - beta0)] + [beta4 * epsilon(t-12)]

This has proved unsuccessful. What equation underlies this arima

prediction? Is there something different that happens

Many thanks for your help,

Keith Campbell

Keith Campbell

Researcher

ROTELLA CAPITAL MANAGEMENT |180 N. Stetson Suite 5100 I Chicago, IL

60601 | t: 312.706.0442 | f: 312.861.0468 |

________________________________________________________________________

_____________________________________________

This message is for the designated recipient only and may contain

privileged, proprietary, or otherwise private information. If you are

not the intended recipient or otherwise believe that you have received

this message in error, please notify the sender immediately and delete

the original. Any other use of this message by you is prohibited.

[[alternative HTML version deleted]]

______________________________________________

R-help@stat.math.ethz.ch mailing list

https://www.stat.math.ethz.ch/mailman/listinfo/r-help

PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

**Next message:**Dirk Eddelbuettel: "Re: [R] RQuantlib ?Windows Binary?"**Previous message:**Paul Bivand: "Re: [R] Tramo-seats"

*
This archive was generated by hypermail 2.1.3
: Mon 31 May 2004 - 23:05:12 EST
*