Panel Estimation with AR-Errors

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

HZem
Posts: 2
Joined: Thu Sep 20, 2018 4:09 am

Panel Estimation with AR-Errors

Postby HZem » Fri Sep 21, 2018 12:58 am

Dear Eviews-community,

The EViews 10 Feature list says that “Estimation with AR errors using nonlinear least squares on a transformed specification” should be possible. Unfortunately I wasn’t able to figure out how to program/estimate it. Could someone help me with this, especially in a panel context?

If I just type “eq_name.ls(cov=cxsur) y c x ar(1)” I get an AR-term in the cross-section but not AR-errors.

Thank you very much for your help

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13294
Joined: Tue Sep 16, 2008 5:38 pm

Re: Panel Estimation with AR-Errors

Postby EViews Gareth » Fri Sep 21, 2018 5:51 am

HZem wrote:I get an AR-term in the cross-section but not AR-errors.



What does that mean?
Follow us on Twitter @IHSEViews

HZem
Posts: 2
Joined: Thu Sep 20, 2018 4:09 am

Re: Panel Estimation with AR-Errors

Postby HZem » Mon Sep 24, 2018 1:23 am

Dear Gareth,
thanks for your quick reply.
With "AR-term in the cross-section" I wanted to say that a lagged dependent variable is included in the regression. Actually, I'd like to estimate pooled GLS with a panel-wide AR(1) correction where the coefficient of the AR(1) process is common to all the panels.

The corresponding STATA-code would look like this: xtpcse y x , correlation(ar1) hetonly

Would be very nice, if you could help me with that.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 6 guests