Page 1 of 1

Panel Conintegrating Regression

Posted: Sun Feb 12, 2012 9:33 am
by lnp3
Dear forum,

I have purchased Eviews-7 recently and am seeking customer support pertaining to "co-integrating regression" in a panel setting.

After having found evidence of co-integrating (or long-run equilibrium) relationships between my variables, I want to estimate my model using Dynamic OLS.

Where is DYNAMIC OLS in panel combo box? It mentions in Eviews Help but I can't see it.

There is GMM in the combo box. however, GMM is not the same as Dynamic OLS.

Please help. I really need your support!!! Am i missing something here?

Best,
:(

Re: Panel Conintegrating Regression

Posted: Sun Feb 12, 2012 12:10 pm
by EViews Gareth
EViews 7 doesn't support panel cointegration estimation.

Re: Panel Conintegrating Regression

Posted: Mon Feb 20, 2012 12:26 pm
by lnp3
Thank you for the feedback.

My question was: I would like to estimate using the fully modified OLS (FMOLS) and dynamic OLS (DOLS), and I wish to find out the E-views command for these processes.

Please see the attachment named "What is new in Eviews 7". In page 4, it mentions " Single equation co-integrating regression estimation using Fully-Modified OLS, Canonical Cointegrating Regression, or Dynamic OLS."

www.eviews.com/EViews7/EViews7WhatsNew.pdf

estimation:
http://www.eviews.com/EViews7/ev7whatsnew.html

I appreciate if you could find out the E-views command for these processes.

Best regards,
Aysen

Re: Panel Conintegrating Regression

Posted: Mon Feb 20, 2012 1:04 pm
by lnp3
I just realized that Eviews 7 supports only time-series co-integration estimation, not panel data.

What is the best model to estimate if there is a co-integrating relationship between my variables in panel data?

In other words, is there any equivalent of dynamic or fully modified OLS in E-views ?

Re: Panel Conintegrating Regression

Posted: Tue Feb 21, 2012 11:56 am
by EViews Glenn