In time series modeling and volatility estimation it is necessary, first remove autocorrelation of time series and after that estimate the volatility model (like GARCH).
the autocorrelation estimate by ACF test, but in some situations (like a low sample data or noise,...) maybe this procedure causes bad estimation of autocorrelation.
for example the true model is AR(3)-GARCH(1,1) but we used AR(1)-GARCH(1,1)
are the GARCH parameters biased in this situation?
Thanks in advance.
Hamidreza Hakimdavoodi ,
Yes, deviation from a true model specification renders parameters biased
See these links:
Article Modelling and forecasting monthly Brent crude oil prices: a ...
Article Comparing the performances of symmetric and asymmetric gener...
Article Comparing the Performances of Artificial Neural Networks Mod...
Dear Hamidreza.
To analyze volatility of a series, you have to first test for the ARCH effect.
This verifies the presence of heteroscedasticity.
If ARCH effect is present, then you can proceed to GARCH models.
In Volatility series, you deal with problem of heteroscedasticity and not autocorrelation.
Regards
- Badges
- Science topic
- Similar topics
- Statistics
- Time Series