arch
arch copied to clipboard
Fitting GARCH model using fixed lags
Is it possible to force the p in the GARCH model to be zero for the first conditional volatility lag and then estimate he rest of the parameters for the rest of the lags?
i.e I wanna be able to fit the following model to the data:
Is it possible to be done in the existing framework?
Sorry, this type of "irregular" GARCH model can't be specified in the package. FWIW, your variance process needs a shock, e.g., epsilon_[t-?]**2
where ? is 1 or 2.
Thanks fro the comment. I was just simplifying the conditional var equation. Although it may seem irregular but it is common practice in the electricity markets as the closest time you can invest in is the 'two' days-ahead market. Do you think it is possible to edit your source code to obtain this?
The only way I could think to do this within the package would be to define a new volatility model that had this structure. I don't think it would be easy to directly extend the existing GARCH model to skip lags.