Page 1 of 1

BVAR reporting error

Posted: Tue Jun 28, 2011 3:23 am
by donihue
Hello Esther/Gareth,

It seems that although the BVAR add-in correctly calculates the parameters when including exogenous variables using the Sims-Zha Normal Wishart prior, it does not report them correctly.

If one compares the results from EViews with those from the "R" programme "MSBVAR" (which was the basis for the original add-in) in this situation, it seems that EViews picks up the value of the estimated constant and places it in the table position for the first exogenous variable, then displacing all the other coefficients downwards one row, so that eventually the reported constant is actually the coefficient of the last exogenous variable. This should be easy to fix.

Whilst on the topic, is there any reason not to allow exogenous variables in the SZ Normal Flat or the Flat-Flat priors cases? (I ask because the MSBVAR programme permits them - non-null "z" matrix with "prior=1" or "prior=2".)

Regards
Donihue

Re: BVAR reporting error

Posted: Sat Jul 23, 2011 9:42 am
by donihue
Returning to this post, I attach for information 2 jpg files indicating the precise reporting problem, should it be of help.

I would also like to reiterate the query in the last sentence of the post:
is there any reason not to allow exogenous variables in the SZ Normal Flat or the Flat-Flat priors cases? (I ask because the MSBVAR programme permits them - non-null "z" matrix with "prior=1" or "prior=2".)
Regards
Donihue

Re: BVAR reporting error

Posted: Wed Jul 27, 2011 4:54 pm
by EViews Esther
I am sorry about the error. I fix the problem in the new version.

Regarding upon a constant "C", while KoKo options will let you choose whether to put "C" into a model (please note that the second dialog will ask you whether to include the intercepts),
Simz-Zha options will include a constant "C" by default. When you write your variables in the first dialog, please do not specify "C".

If you would like to include exogenous variables in the flat-flat prior models, I would recommend you to do classical VAR estimation.
As you know, flat-flat priors are noninformative priors so that either classical or bayesian VAR will produce the same results.

Thank you for your patience.

Best,
Esther

Re: BVAR reporting error

Posted: Thu Jul 28, 2011 2:02 am
by donihue
Many thanks for the fix, Esther.
Regards
Donihue