On Thu, 17 Jan 2019, Sven Schreiber wrote:
To provide some background, the help for 'arch' says:
"This command is
retained at present for backward compatibility, but you are better off using
the maximum likelihood estimator offered by the garch command; for a plain
ARCH model, set the first GARCH parameter to 0."
In the GUI you also go directly through garch and then you can save the
predicted variance from the menu.
(BTW, doing 'arch 1 r' --i.e. specifying no explicit constant-- provokes just
a generic data error. I think the error message could be more informative.
Apart from that, aren't there legitimate cases where you are working with
mean-zero series?)
Would it be unthinkable to just retire the "arch" command?
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------