Problem with VAR model (Normality test)

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

thanhtung3008
Posts: 1
Joined: Wed Nov 09, 2011 10:03 am

Problem with VAR model (Normality test)

Postby thanhtung3008 » Wed Nov 09, 2011 10:14 am

In my VAR model, after I had taken the normality test, the result showed that I had 3 equations in which the residual was not normal (out of 6 equations)
In other test, my model was passed.
Can these problems with normality test affect "impulse response" result? How I can solve these problems?
Because I am a student from a university and I have not learned VAR model in uni. I just learn by myself so please help me with these problems.
Thank you so much

erdogancevher
Posts: 1
Joined: Thu Oct 31, 2013 2:50 am

Re: Problem with VAR model (Normality test)

Postby erdogancevher » Thu Oct 31, 2013 2:53 am

Normality in VAR:
As far as I know:
1. Normality is NOT needed when Granger causality analysis of VAR and Impulse -Response of VAR
2. Normality IS important when testing cointegration via Johansen tests in constructing Likelihood Function.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests