0
$\begingroup$

I was wondering if there are any other things that I can say about the differences between these 2 models, besides the comments about the ACF and PACF. Specifically, I was wondering which model would be easier to forecast with, if that makes any sense, and why.

$\endgroup$

1 Answer 1

2
$\begingroup$

As you can see here ( http://en.wikipedia.org/wiki/Autoregressive%E2%80%93moving-average_model#ARMA_model ) the ARMA(2,1) will only depend on the last two values, and on the last noise variable, when the ARMA(13,9) will consider 13 values to the past and 9 past noise variables. To forecast it all depends on your what you're trying to forecast. If your variables do not depend strongly on lots of values in the past, you can use the ARMA(2,1). It all depends on the nature of what you're trying to predict.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.