There is often a very simple way around this. For example if you want
to restrict the coefficients of X! and X2 to be equal simply create a
variable X12 = X1 + X2 and simply include the variable X12 in the
restricted estimation. All the standard results of the estimation
method will then be available to you.
Best Regards
John
2011/5/29 Javier García <javigarcia83(a)yahoo.es>:
Hi everybody:
After applying OLS (or another method) to estimate an equation you have the
possibility of introducing some lineal restrictions in the model, but in the
output of the restricted method Gretl only gives the estimators and little
more. It could be possible to have more information (Squared-R, information
criteria,…) and a menu similar to the one of the unrestricted model (with
tests of heterocedasticity, normality,…)? SUR models, for example, give more
possibilities (although not all).
Cheers
Javi
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
--
John C Frain
Economics Department
Trinity College Dublin
Dublin 2
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:frainj@tcd.ie
mailto:frainj@gmail.com