Re: [Gretl-users] Tests for GARCH models
Many thank. I've downloaded the snapshot version and testes them.
Perhaps, the autocorrelation and ARCH tests on "standardized"
residuals (of course, if one checks the option for standardizing the
residuals) should be helpful on diagnoses of "no remaining"
autocorrelation and GARCH.
Surely, one can save the standardized residuals and squared residuals
as series into main windows to do these tests himself. But having
these test "inside" the estimated GARCH model windows (rather than
going back to the "outside" main window) would be more convenient.
Best regards.
Yi-Nung
2009/5/7 Allin Cottrell <cottrell(a)wfu.edu>:
On Thu, 7 May 2009, yinung at Gmail wrote:
> In general, after estimating a GARCH, the diagnosis should be on
> "standardized" residuals rather than on "regular" residuals from
the
> mean equation.
I've now added an option --stdresid to the garch command (and also
a corresponding GUI checkbox). This standardizes the residuals.
> However, the current test (named ARCH) with a GARCH model via GUI is
> on "regular" residuals from the mean equation.
The regular ARCH test shouldn't be available for GARCH models;
that bug is now fixed.
> In addition, the tests on "normality of residual" and
> "autocorrelation" is now disabled with a GARCH model. Are they
> possibly enabled (and on the "standardized" residuals)?
The normality test is now enabled. I'm not sure what an
autocorrelation test would look like for a GARCH model, but you
have the Box-Pierce Q statistic that's given with the residual
correlogram.
Allin.
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users