I am working with an ARDL model in STATA but am unable to figure out how to run the impulse response functions with the estimated coefficients. Numerous papers talk about ARDL and IRF, but not a single one I've found actually outlines the process.

Can anyone point me in the right direction?

  • $\begingroup$ try to check the step response function suggested by ben volgevand in his book applied econometric.contact timmexdareal@gmail.com $\endgroup$ – user7772 Mar 28 '16 at 21:12

In order to compute IRF in stata you should check "varbasic" in Stata's manual: http://www.stata.com/manuals13/tsvarbasic.pdf

  • 2
    $\begingroup$ The problem is that ARDL is a single equation framework with identification restrictions on the underlying VAR. In my case, I am estimating a coitegrating relationship through an ARDL specification. Even when I try to restrict the VECM in stata according to the ARDL restrictions, my results are not the same. So taking the IRF from the VAR or VECM seems incorrect, because the estimates are different. What I really want to know is how to get IRFs for single equation frameworks such as the bounds testing approach suggested by Pesaran et al. $\endgroup$ – user4046 Feb 26 '15 at 1:19

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.