Timeline for DCC GARCH - specifying ARCH and GARCH parameter matrices in Stata
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 13, 2017 at 12:44 | history | edited | CommunityBot |
replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
|
|
| Aug 16, 2016 at 14:05 | vote | accept | cassius | ||
| Mar 22, 2015 at 6:33 | comment | added | Richard Hardy | VAR model was just an example where spillover effects are in conditional mean, not conditional variance. So VECH-GARCH is the one. | |
| Mar 21, 2015 at 23:15 | comment | added | cassius | Thanks Richard! You've suggested that to find a model that allow for spillover effects i should look for VECH-GARCH and VAR model. Vech-GARCH i understand but i did not find a work with VAR for this subject. Could you give me a direction and suggest some work with Var? Thanks, again. | |
| Mar 21, 2015 at 18:49 | comment | added | Richard Hardy |
I think ccgarch may be quite a unique package that implements EDCC (extended DCC) models extra to the simple DCC. It's been a while since I tried it out myself so I have largely forgotten what's in there. But I took a look at the package creator's PhD thesis here and it seems that you got EDCC model right. However, I doubt Stata allows for this kind of flexibility.
|
|
| Mar 21, 2015 at 17:49 | comment | added | cassius | Thanks, Richard! I had this doubt because i saw the pdf of R package: CCCGARCH and this package allows me to implement this option. The estimation code goes like this: dcc.estimation(inia, iniA, iniB, ini.dcc, dvar, model, method="BFGS", gradient=1, message=1) And when i set: model="extended" i get a full ARCH and GARCH Matrices. Am i right? | |
| Mar 21, 2015 at 10:49 | history | edited | Richard Hardy | CC BY-SA 3.0 |
added 7 characters in body
|
| Mar 21, 2015 at 10:41 | history | answered | Richard Hardy | CC BY-SA 3.0 |