Hi,

I have 2000 obs. in total which is 5 minutes realised variance. I will have an HAR model (for example: ols x constant x(-1) a b) with an initial sample 1-500 obs. and I am going to forecast 501. obs. Next, I will have the initial sample 2-501 obs. and forecast 502. obs. And again initial sample 3-502 and forecast 503. obs. ... up until 2000. obs. Each time, I need to re-estimate my HAR model with initial sample and forecast next one, which is rolling windows forecasting. 

I could not find the codes for this purpose. Is it possible to do that in gretl? 

Many Thanks,