Re: [Gretl-devel] a small issue with $model.ainfo for arima
Thank you!
I guess it was not difficult,
but there's a question of priorities.
So, thank you again!
Oleh
6 листопада 2018, 16:49:30, від "Allin Cottrell" <cottrell(a)wfu.edu>:
On Tue, 6 Nov 2018, Allin Cottrell wrote:
On Tue, 6 Nov 2018, oleg_komashko(a)ukr.net wrote:
> Dear all,
> On viewing $model bundle content
> ainfo is indicated as list while it
> looks like 1X9 matrix, a kind of
> {p,q,P,Q,x5,x6,d,D,$pd}
> I have always obtained x5=p,x6=q
> It seems, it should be indicated as a matrix
> Also, what are x5 and x6?
I guess it should be set as a matrix, though it's all just integers. x5 and
x6 are, respectively, the numbers of non-seasonal AR and MA coefficients, np
and nq. These numbers will equal p and q (the maximum non-seasonal AR and MA
lags) unless the specification is "gappy". For example, if the AR spec is
given as {1,4} we'd have p = 4 but np = 2.
"ainfo" now appears as a matrix in the $model bundle after arma
estimation. In addition, the roots now appear as a matrix under the
name "roots". At present this is an old-style representation of a
complex matrix, with real part in column 1 and imaginary part in
column 2.
Allin
_______________________________________________
Gretl-devel mailing list
Gretl-devel(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-devel
Attachments:
- attachment.html (text/html — 2.8 KB)