Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: VAR model and significance of coefficients
From
"Sabina Kummer" <[email protected]>
To
[email protected]
Subject
st: VAR model and significance of coefficients
Date
Wed, 13 Mar 2013 18:10:59 +0100 (CET)
Dear all,
I have a question regarding the interpretation of the coefficients of a VAR/VEC specification.
In a VAR/VEC model, the coefficients are all endogenous and dependant from each other (multicollinear). This implies that the t-statistics (Student statistics) of the various coefficients are biased. Thus, I would like to know how to interpret the significance of the coefficients and how to be sure that the choice of the explanatory variables is adequate.
Should I consider the F-test for the “global significance” of the model (i.e. the significance of all the coefficients altogether)?
Or should I consider the t-stat but only as a "soft indication" about the significance of the coefficients?
Thank you very much for your help and your consideration.
Best regards,
Sabina
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/