Re: time series in R

About this list Date view Thread view Subject view Author view Other groups

Subject: Re: time series in R
From: Paul Gilbert (pgilbert@bank-banque-canada.ca)
Date: Tue 20 Jul 1999 - 07:37:04 EST


Message-ID: <37939A80.3BF10D12@bank-banque-canada.ca>

> 4. The notation for ARMA models may well be the stuff that
> holy wars are made of,
...
For this episode of the war perhaps we should stick with univariate
arima as in S, and use the same notation. For the multivariate episode I
like

A(L) y(t) = B(L) e(t) + C(L) u(t)

for ARMA models and

z(t) = F z(t-1) + G u(t) +K e(t-1)
y(t) = H z(t) + e(t)

for state-space models. I think it is important to think about
state-space and ARMA together, in order to try and have a consistent
approach.

Paul Gilbert

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._


About this list Date view Thread view Subject view Author view Other groups

This archive was generated by hypermail 2b25 : Tue 04 Jan 2000 - 14:16:06 EST