Re: [Gretl-users] ARMA bug?
On Tue, 31 Jan 2006, John Paravantis wrote:
Methinks I found a bug in ARMA.
[ data series snipped -- but thanks for providing this ]
Then try to run an ARMA(1,1): you get a dialog that "The
convergence criterion is not met". Unfortunately, it is possible
to fiddle with the convergence criterios (# of iterations) on the
ARMA dialog box!
Here comes worse. Try to estimate an ARMA(0,1) WITHOUT THE
CONSTANT: you get an "out of memory error"!
I'm not sure precisely what feature of the data or gretl's methods
is responsible for the non-convergence in your first model.
Perhaps Jack will have an idea on that. But note that in gretl you
have the option of using X-12-ARIMA for ARMA estimation, and in this
case it will produce estimates for you.
As for the "out of memory" error in the second case, that is indeed
a bug, now fixed in gretl CVS. Gretl's native ARMA module will
estimate the second model OK with this bug fixed (and in reasonable
agreement with X-12-ARIMA).
? arma 0 1 ; x --nc
Convergence achieved after 7 iterations
ARMA estimates using the 30 observations 1971-2000
Dependent variable: x
VARIABLE COEFFICIENT STDERROR T STAT P-VALUE
e(-1) -0.218822 0.207045 -1.057 0.29929
Allin Cottrell