Fixed Effects Estimation

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

EconometricAarhus
Posts: 4
Joined: Wed Mar 25, 2015 1:50 am

Fixed Effects Estimation

Postby EconometricAarhus » Wed Mar 25, 2015 2:15 am

Hello.

Using EViews 7.

I have uploaded the Excel file "EViewsPanelDataFEquestion", which is a more simple version of my extensive data.

I am trying to make a panel data regression and get the problem with "Near Singular Matrix". My problem is when I do my regression including two constants (hh and ii) and including cross section fixed effects it tells me "Near Singular Matrix". The length is the same for all variables and so on. I have read some articles where they include these variables without problems. They use Stata and I use EViews. I can make the regression without effects, with period fixed effects, with period random effects and cross section random effects.

What seems to be the problem? And how do i fix it?

(I hope I'm posting it the correct place).

Best regards
Attachments
EViewsPanelDataFEquestion.xlsx
(1.77 MiB) Downloaded 114 times

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12724
Joined: Tue Sep 16, 2008 5:38 pm

Re: Fixed Effects Estimation

Postby EViews Gareth » Wed Mar 25, 2015 10:18 am

A fixed effect is just a variable that is constant across time (i.e. it takes the same value for all time periods in each cross-section). You have variables that already do that. Thus you have perfect collinearity. This is a mathematical issue, and not an EViews one.
Follow us on Twitter @IHSEViews


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 19 guests