[R] MA parameter in R vs. Minitab

[Turner Rolf]

Erin Hodgess wrote:

Dear R People:

I ran an ARIMA(1,0,1) on a particular series in R and got a negative
MA(1) estimate.

Then I ran an ARIMA(1,0,1) on the same series in Minitab and got a
positive MA(1) estimate.

The values are about -0.69 and 0.70.

Does R show the opposite value, please?

Uh, yes.  In R an ARMA(p,q) model is written (sensibly) as

X[t] = a[1]X[t-1] + ... + a[p]X[t-p] + e[t] + b[1]e[t-1] + ... + b[q]e[t-q]

See ?arima.

Note the plus signs all the way.

In MINITAB the (to my mind) somewhat inexplicable convention set down in
Box and Jenkins' seminal text book is used:

X[t] = a[1]X[t-1] + ... + a[p]X[t-p] + e[t] - b[1]e[t-1] - ... - b[q]e[t-q]

Note the minus signs.  This explains the difference that you see.

These things seem to be deliberately put in place to make life as confusing
as possible for us bunnies.  Psigh.

         cheers,

                Rolf
######################################################################
Attention: 
This e-mail message is privileged and confidential. If you are not the 
intended recipient please delete the message and notify the sender. 
Any views or opinions presented are solely those of the author.

This e-mail has been scanned and cleared by MailMarshal 
www.marshalsoftware.com
######################################################################