Bayesian VAR IRF - standard errors

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

chartwel
Posts: 14
Joined: Tue Mar 02, 2010 5:00 pm

Bayesian VAR IRF - standard errors

Postby chartwel » Fri Oct 13, 2017 8:15 am

Hi,

I'm doing some work with Bayesian VARs and I would like the impulse response function to include at least 1 if not 2 SD standard errors. I know that EViews doesn't support it at this time, but I also know that there should be a way to save the S.E.s as a matrix and do it manually. For the life of me, though, I don't have the skill or knowledge on how to do that. Could someone walk me through how to save the SEs as a matrix from a BVAR? Specifically using the built-in interface or by providing the code?

Thanks!

chartwel
Posts: 14
Joined: Tue Mar 02, 2010 5:00 pm

Re: Bayesian VAR IRF - standard errors

Postby chartwel » Fri Oct 13, 2017 8:26 am

As an example, I use this code to try and figure out the IRG:

var5.impulse(12, m, smat=myownimpulse, imp=chol) y x @y @x

but it continually gives me "error in specification of innovations or responses."

Is there something I'm missing?


Return to “Estimation”

Who is online

Users browsing this forum: Google [Bot] and 29 guests