Page 2 of 2
Re: Dueker JBES 1997 MS-GARCH models
Posted: Thu Jun 22, 2017 12:34 pm
by TomDoan
Most likely, none of the above. Do you have any reason to believe that any form of MS model is required?
Re: Dueker JBES 1997 MS-GARCH models
Posted: Thu Jun 22, 2017 1:59 pm
by jack
I am really sorry for asking so many questions.
I do not have a clear reason to believe that any form of MS model is required. I just want to see if introduction of exchange rate futures contract has brought about a high volatility regime in spot market. I want to see if this event has increased the volatility. As I said before the methodology is based on this paper.
http://onlinelibrary.wiley.com/doi/10.1 ... 3/abstract.
Re: Dueker JBES 1997 MS-GARCH models
Posted: Thu Jun 22, 2017 2:11 pm
by TomDoan
There are other types of "switching" besides Markov switching. If you have a date-certain at which there has been a change, then do a GARCH-X model with a dummy for the period where things change.
Re: Dueker JBES 1997 MS-GARCH models
Posted: Thu Jun 22, 2017 2:41 pm
by jack
Thank you for your suggestion.
Can I estimate GARCH-X models in RATS?
Re: Dueker JBES 1997 MS-GARCH models
Posted: Tue Jan 30, 2018 3:31 pm
by TomDoan
Yes. See Section 9.3.6 in the User's Guide.