Re: [Gretl-devel] $vcv in vecm
On Thu, 7 Jan 2010, Sven Schreiber wrote:
Allin Cottrell schrieb:
> The only "missing" accessor is $vcv for VECMs. That's because
> I don't know what to do about the covariance block for \beta
> and the other coefficients.
>
Well what one *could* do is to treat the error-correction terms
as given due to the super-consistency (T-convergence) of the
cointegration coefficients, and then the remaining system is
just multi-equation OLS.
OK, I've added $vcv for VECMs on that basis. However, we don't
attempt it at present if \alpha is restricted. Example:
open data9-7
vecm 4 1 1 2 3
matrix V = $vcv
V
matrix SE = $stderr
SE
matrix SE2 = mshape(sqrt(diag(V)), 11, 3)
SE2
Allin.