Lars,

Your questions are about VARs in general, not about Gretl. This list is for questions specific to Gretl, not general questions about econometric methods. If you’re asking about how Gretl computes things like IRFs, for example, that’s covered in chapter 29 of the user’s guide. For questions about the methods, please consult other sources (e.g., Enders’s textbook, the blog that was recommended to you earlier, etc.).

Best,

Peter

From: gretl-users-bounces@lists.wfu.edu [mailto:gretl-users-bounces@lists.wfu.edu] On Behalf Of lasses skola
Sent: Monday, April 30, 2018 11:43 AM
To: Gretl list
Subject: Re: [Gretl-users] VECM and IRF interpretation

I'm sorry but your answer is not helping me much, it only raises new questions for me. WHAT does the speed of adjustment say about real changes in the variable I am interested in? WHAT is equilibrium in this context, more than just an abstract theoretical construct? HOW do I interpret the changes in the IRF?

More specifically, I would like to know what unit the changes in the IRF measured in. Is it one standard deviation shock in the independent variable on the dependent variable, measured in the unit of a standard deviation in the dependent variable of the independent variable? Yes, I know a VAR/VEC is a system etc.

Cheers,

Lars

2018-04-29 12:14 GMT+02:00 Sven Schreiber <svetosch@gmx.net>:

Am 27.04.2018 um 20:28 schrieb lasses skola:

Hi! I have a question regarding VECM and IRF interpretation in Gretl.

Hi, to be clear, this is not about an interpretation _in Gretl_, it's a more generic question, there's nothing gretl specific here.
Which -I presume- is why no answers have followed so far.

According to the speed of adjustment coefficient in the VEC, the target variable adjusts at a speed of 15,5% per year to equilibrium. But the IRF says that the cumulative change in the target variable is only 2% from year four trough the time horizon of the IRF, which is nine years. How can I interpret this?

This is a system there is no such thing as *the* target variable.
Apart from that, the two magnitudes have very little in common. You could have a case where the first variable is not reacting/adjusting at all to disequilibria, and still you could get a long-run permanent effect because of the other dynamics.

cheers,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users