Hi Radost

There is not a big difference between Eviews7 and Eviews 8.(However, a Bayesian Var was added to the Var specification window) .To perform PVAR, the easiest way is to use Stata (pvar.ado). I recommed you to read the paper of Inessa Love & Lea Ziccino (2006), (Financial Development and Dynamic Investment Behavior: evidence from Panel VAR”The Quarterly Review of Economics and Finance, 46/190-210.) in which they explained thouroughtly how to use the Pvar.do programs in their paper.

Regards

H.H

@Helmi Hamdi: I have read the paper you recommend but I cannot find the instruction for using STATA to estimate PVAR in this paper. Could you please explain me more about this? Thank you so much.

 Hello Thu Thi Anh Tran:

The Package of Panel Var programs   is available  at the following link ((zipped file, 26kb):

http://siteresources.worldbank.org/INTRES/Resources/ILove_var.zip

or you can go to the author's website at google sites:

https://sites.google.com/a/hawaii.edu/inessalove/home/research

you can also have a look at the link below where you can find a very similar Inessa'  Pvar.do code

http://www.rdecker.net/code

Regards

Helmi HAMDI, PhD

Hi Helmi Hamdi,

I have got it. Thank you very much for your clear instruction. By the way, have you heard about xtlsdvc in STATA (Bruno 2005). I have found some people using it to run Panel VAR model when N is small and T is relatively large.

Regards,

The procedure to build a VAR model involves the following steps:

You could estimate a standard VAR and use @expand(@Crossid) as an exogenous variable which might give you the fixed effects you want.