Sorry, my fault, thanks for responding. I am adding my data to the email. I have 5-minute realised variance data for FTSE.

Basically, I am trying to do rolling windows forecasting using the HAR-RV model (in time series). I will have the initial sample;  observation 24-336 (I labelled observation date as numbers). Observations between 337-437 will be the out-of-sample. First, I want to estimate HAR model with 24-336 obs. and then forecast one-step-ahead forecast [337]. Next, estimate HAR with 25-337 obs. and then forecast [338]. Estimate with 26-338 and then forecast [339] ...

I am not sure I am doing right with my codes and in my case rolling windows forecasting is; one-step-ahead forecasted values are generated by each sliding different HAR model (i.e. 24-336, 25-337, 26-338 ...). I am doing that with HAR-RV model and later on, I will add to the model as an exogenous variable –VIX, EPU, Industrial production etc.– and compare forecasting performance. 

HAR-RV model is:
FTSE.RV=CONSTANT+FTSE.RV(-1)+FTSE.WEEKLY.AVERAGE+FTSE.MONTHLY.AVERAGE

FTSE.WEEKLY.AVERAGE=FTSE[(-1)+(-2)...+(-5)]/5
FTSE.MONTHLY.AVERAGE=FTSE[(-1)+(-2)...+(-22)]/22

Thank you very much,
On Friday, May 15, 2020, 10:56:40 PM GMT+1, Sven Schreiber <svetosch@gmx.net> wrote:


Am 14.05.2020 um 02:05 schrieb Burak Korkusuz:
> I am trying to write code for the rolling windows forecasting using
> HAR-RV model.
> My codes are:

Again I would ask you to send codes that can actually be run. You're
using undocumented and/or unavailable datasets in your examples. This
makes it difficult to help you.



> set verbose off
>      loop i=1..100 -q
>      smpl 23+i 335+i
>      ols RV5_FTSE const RV5_FTSE(-1) HARWEEK HARMONTH
>      fcast 337 437 1 forecasted --rolling


Next, please stop using the option "--rolling". This is still working
for compatibility reasons but was renamed to "--recursive" in gretl
2017d (see http://gretl.sourceforge.net/Backward.html). This is
important because "rolling" was an ambiguous term. How do you define
rolling in your case, what exactly do you want to achieve?

cheers
sven
_______________________________________________
Gretl-users mailing list -- gretl-users@gretlml.univpm.it
To unsubscribe send an email to gretl-users-leave@gretlml.univpm.it
Website: https://gretlml.univpm.it/postorius/lists/gretl-users.gretlml.univpm.it/