[R] r: arma fitting

[Pfaff, Bernhard]

> 
> hi all
> 
> i would like to model an AR model of the following form:
> 
> y(t) = a + p*y(t-5) + e(t)
> 

Hello Allan,

why not simply lm(), such as below?

n <- length(y)
lm(y[-c(1:5)] ~ y[-c((n-4):n)])

or, alternatively you could restrict coefficients ar(1) to ar(4) to zero by
using:

arima(y, order=c(5, 0, 0), fixed=c(0, 0, 0, 0, NA, NA), method="CSS")

HTH,
Bernhard


> where :
> 
> y(t) is the value of y at time t
> a is a constant
> p is the coefficient of the 5th lagged term
> {e} is a normal error series
> 
> Any help will be appreciated
> Allan
> 
> ______________________________________________
> R-help at 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
> 


--------------------------------------------------------------------------------
The information contained herein is confidential and is inte...{{dropped}}