Simple question on the eviews estimation method for VECMs

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

carbovins
Posts: 7
Joined: Tue May 17, 2011 10:04 am

Simple question on the eviews estimation method for VECMs

Postby carbovins » Wed May 18, 2011 12:56 am

Hello,

I just want to know what is the estimation method used by eviews to estimate a vecm? Ols? Maximum Likelihood?
I can't find the answer in the users' guide.
Thank you.

Vincent

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13604
Joined: Tue Sep 16, 2008 5:38 pm

Re: Simple question on the eviews estimation method for VECM

Postby EViews Gareth » Wed May 18, 2011 10:26 am

ML is used to estimate the cointegrating vectors. I believe the method is outlined in the Johansen papers/books in the User Guide references.

carbovins
Posts: 7
Joined: Tue May 17, 2011 10:04 am

Re: Simple question on the eviews estimation method for VECM

Postby carbovins » Thu May 19, 2011 1:40 am

ML is used for cointegration equation, but what is the method for the VAR part of the VECM? In the Johansen (1991) paper, ML is used in both cases, but I'm not that it is the case in Eviews. Can you hlep me please?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13604
Joined: Tue Sep 16, 2008 5:38 pm

Re: Simple question on the eviews estimation method for VECM

Postby EViews Gareth » Thu May 19, 2011 8:14 am

The other coefficients are estimated by the "two stage estimation" procedure outlined on page 301 of Lutkepohl 2005 - New Introduction to Multiple Time Series Analysis.

carbovins
Posts: 7
Joined: Tue May 17, 2011 10:04 am

Re: Simple question on the eviews estimation method for VECM

Postby carbovins » Fri May 20, 2011 6:04 am

two stage ols?


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 1 guest