I'm using MSGARCH package in R. By return_data/Volatility(fit.model), I get the residuals. When I calculate the standard deviation of the residuals, it turns out that it's close to 1 for all residuals. However, the standard deviation in each regime differs greatly. It's about 0.7 in one and 1.6 in the other.
Why is it? I thought that the residuals would have unit variance in each regime respectively, since in each regime they are filtered by a GARCH model.
(This package follows the paper A New Approach to Markov-Switching GARCH Models in model specification.)
Yes. But after divided by the volatility, the standard deviation of standardized residuals are still different in 2 regimes. Ette Etuk
You can assume that the variance is regime specific and estimate the model with this assumption, or you can assume that it does not depend on the regime and estimate that one. It depends on your assumption.
Tihana Škrinjarić The variance of residuals is supposed to be 1 in any GARCH. At least in the paper which this R package follows, it's N(0,1). But this is not the case when I test the residuals using the package.
Ooh sorry, yes the residual variance is 1 always. How do you extract the residuals from the fitted model?
By return_data/Volatility(fit.model), where return_data is the data, and Volatility is the function provided by the package.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R