[Gretl-users] Exact collinearity and modprint

Giuseppe Vittucci ignatiusreilly75 at yahoo.it
Thu Nov 3 22:17:18 EDT 2011


Thanks a lot.
Giuseppe

To Allin: 
The regression is actually just a FE panel data model, but it follows a
concentrated NLS to estimate a Panel Smooth Transition Regression model.
So, I would like to have more control on the output (s.e. and
statistics). 

On Thu, 2011-11-03 at 15:14 +0100, Ignacio Diaz-Emparanza wrote:
> El 03/11/11 10:31, Giuseppe Vittucci escribió:
> > Dear all,
> >
> > when in a regression one or more variables are omitted due to exact
> > collinearity, the command modprint leads to misleading results cause the
> > initial list of regressors does not match the vector of coefficients
> > returned by gretl.
> >
> > Is there a way to retrieve the list of regressors dropped by gretl or
> > the list of regressors eventually used in the regression?
> >
> > Thanks
> > Giuseppe
> 
> yes. This is automatically saved in $xlist you may call it after the 
> estimation command by means of for example:
> 
> list listname = $xlist
> 
> 





More information about the Gretl-users mailing list