EViews.com

Hello,

I am using Eviews 8.1 and have really appreciated the incorporation of BVARs into the software.

I did have some questions about the model which I couldnt find in the EVIEWs help file. Is it a gibbs sampling model? If so, is there a set number of iterations used to calculate the coefficients? Finally, are gibbs iterations discarded as a burn in?

I ask because a model I have developed has issues of autocorrelation and I am wondering if a lack of burn in is causing the model to be unstable.

Thanks!

Poached Wonk

From the manual:

It is worth noting that EViews only offers conjugate priors (whose posterior has the same distributional family as the prior distribution). This restriction allows for analytical calculation of the Bayesian VAR, rather than simulation-based estimation (e.g. the MCMC method) as is generally required.

I see! Thank you very much!