Le mer. 20 janv. 2021 à 15:05, Sven Schreiber <svetosch@gmx.net> a écrit :
..but in principle it seems easy enough to compute a fitted value yhat even for any obs (y-X-constellation) which wasn't part of the estimation sample. I mean that's what we do for prediction, no?

Yes Sven, by all means :) (that was not a very wise question of mine) 

Does a (static) "fcast" work there in gretl?

No, it doesn't. For 0-weighted observations excluded from the estimation the "fcast --static" gives a "nan" value.

Best
Artur