[Gretl-users] maximum like. conditions

Berend Hasselman bhh at xs4all.nl
Sun Nov 29 12:29:43 EST 2009


On 29-11-2009, at 18:06, Allin Cottrell wrote:
> 
> ;-) This is a subtle bug (if it's a bug; I'm not sure) with an
> easy workaround.  With the initialization
> 
> scalar alpha = 0.4
> scalar beta = 0
> 
> The "check" condition -- alpha>0 && beta>0 -- is violated on the
> first iteration.  Therefore the formula for "ll" comes down to
> 
> ll = NA
> 
> This generates a scalar value, which is not allowed in the mle
> context.  The fix is to initialize such that the check is
> satisfied on the first round, e.g.
> 
> scalar beta = 0.001

I should have seen that.

I don't think you can call this a bug.
But a different error message (got scalar, expected <...> for likelihood in mle ) would be nice.

Berend


More information about the Gretl-users mailing list