Dear Gretl Team,
I would like to suggest some improvements (I think ;-)) to the VAR model window. My aim goal is to make VAR model window more close to OLS model window in terms of "easiness of use". Additionally, it would be a good change for Gretl 2.0. Some of the suggestions have been inspired by EViews.
(1) Impulse-response: I think it could be useful if we had more options regarding to the impulses. EViews has the option "impulse definition" where we can choose the decomposition method (Residual - one unit; residual - one std. deviation; Cholesky - dof adjusted; Cholesky - no dof adjustment; generalized impulses; structural decomposition; and user specified.
(2) Impulse-response and variance decomposition: It would be great if we had the option "Cholesky ordering" (I know we can choose this before the estimation, but I think this is not so good).
(3) Granger causality test: I think the test
should be more explicit, just as tests of OLS are (ie, the results should
only appear when it was requested). The unaware user may not realize
that the results that appear below the estimated equations are nothing more
than the Granger causality test. Thus, after the VAR estimation, we could select "Tests -> Granger Causality Test" and the following result would appear:
Granger causality test -
Null hypothesis: "v1" does not cause "v2"
Test statistic: F(1, 72) = 1,6655
with p-value = P(F(1, 72) > 1,6655) = 0,2010
I really don't know how difficult are this (in terms of code), but I
think it would be very nice ;)
Henrique C. de Andrade
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge