Re: [Gretl-users] Periodogram Values - Comparison with Statistica 9.0
On Fri, 5 Feb 2010, Sven Schreiber wrote:
savos schmagges schrieb:
> Thank you so much!
>
> Do you see a chance to compute a cross-periodogram with gretl? I am now
> experimenting to compute it with gretl...when I get it, I want to post
> it for you. But maybe you have already achieved it?
>
For these kind of things Jack typically has some one-liners that he
thinks are totally obvious and which are the reason why no readymade
additional functions should be introduced in this part of the gretl
universe ;-)
In this case, I haven't. In fact, although fft()/ffti() is nice to have in
stock, the fact that we don't handle complex numbers natively probably
means that multivariate spectra will never be gretl's forte. In fact, for
complex numbers-related tasks, we probably ought to add matlab/octave to
the list of external packages supported via "foreign".
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti