Dear colleagues, First of all, many thanks for gretl. I am using it with my students and research activities since last year, and I do really enjoy it.
One small issue raised concerning the goodness-of-fit test for OLS models which don't have the intercept term. As far as I understand, gretl computes the common R-squared for intercept models, and uncentered R-squared. It is known that in such models the uncentered is very likely to be close to 1, hence it becomes uninformative. Would it be possible to include the option for choosing, what kind of R-squared will be computed for non-intercept models? Best regards, Anton Pyzhev, Assistant Professor at the Institute of Economics, Management and Environmental Studies, Siberian Federal University, Krasnoyarsk, Russia