[Gretl-users] Implement new criterion for var lag selection

Allin Cottrell cottrell at wfu.edu
Tue Jul 9 10:25:24 EDT 2013


On Tue, 9 Jul 2013, Gian Lorenzo Spisso wrote:

> I would like to implement in GRETL the procedure for lag selection of a VAR
> as specified here:
> http://www.tandfonline.com/doi/pdf/10.1080/1350485022000041050 which
> essentialy replace BIC and HQC with a weighted average of the two.

You can easily calculate the average of the two criteria, which 
gives what Hatemi-J calls the "HJC". For example,

<hansl>
open data9-7
var 6 PRIME UNEMP --lagselect
matrix IC = $test
# average BIC and HQC
matrix HJC = (IC[,2] + IC[,3]) / 2
print HJC
</hansl>

However, the paper that recommends this criterion is quite strange: 
it provides no evidence that the averaged value out-performs either 
of the individual criteria. It reports a Monte Carlo simulation, but 
only gives results for HJC! No comparison is even attempted.

Allin Cottrell



More information about the Gretl-users mailing list