Re: [Gretl-users] out of sample forecasting
yadong li wrote:
is there any way to obtain out of sample R square using Gretl ?
I tried many time but couldn't figure it out.
I would say, by definition an
out-of sample R-square couldn't exist.
http://encyclopedia.thefreedictionary.com/R+Square
The reason for that is, that the R-square is calculated using the
difference between the model and the actuals. So it's kind of hard to
get it if there are no actuals ;-)
Johannes
appreciate for help
best,
yadong
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users