Page 1 of 1

Help with VAR and Granger Causality

Posted: Sun Aug 01, 2010 7:38 pm
by Herbo
If I have I(2), I(1) and I(0) variables as my VAR variables, I second
difference I(2) variable and difference I(1) variable and use these
differenced and I(0)
variables in my VAR.

1) To make interpretations of VARGRANGER, can I refer to the original
variables as if differencing is not an issue, or do I have to take
precautions in interpretations?

2) Do I have to check for possible cointegration between the differenced and
I(0) variables?

I read many books and articles about these questions. I think I know the
answers, but I want to make sure that I am doing right.

If possible please point to references that may shed more light on my
questions.

Thanks in advance,

Herbo