Hi,I am trying to write code for the rolling windows forecasting using HAR-RV model.My
codes are:
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 endloop
I am not sure whether my forecasted values are rolling windows forecasts or not. I can see
on the script I succeeded re-estimated rolling windows regressions (that s why i did not
put -q there). But, I am not sure my one-step-ahead forecasted values are generated with
sliding re-estimated regressions. [I am not sure should I change my 5th line with fcast
336+i 336+i 1 forecasted --rolling] Or what should I do to get one-step-ahead rolling
windows forecasts in this loop command?
Does anyone know about that. I think I am missing something here on codes. I am sorry I am
making busy this line about this a couple of times, but I am trying to understand and
there is no one i can ask about that except here.
Thank you very much.