I tried to use bivariate EGARCH model to explain the volatility dependence structure between the U.S. stock market & the China stock market. It gives weird results, and my supervisors told me that, technically speaking, EGARCH can be used for two different variables, but they actually have not come across this application every often. It might be reasonable to say that they have never seen it before... Most of the time, univariate EGARCH is used. Has anyone come across the same issue?
I am really keen to know your opinions and much appreciate your time.
Neither univariate not multivariate EGARCH has an underlying stochastic process that leads to its derivation, no regularity conditions, no likelihood equation, no Jacobian or Hessian matrices, and hence no asymptotic properties of the QMLE.
In short, EGARCH has no statistical properties.
It might be useful to read the following short papers on EGARCH:
“A one line derivation of EGARCH”, Econometrics, 2(2), 2014, 92-97.
“The correct regularity condition and interpretation of asymmetry in EGARCH”, Economics Letters, 161, 2017, 52-55.
“On the invertibility of EGARCH(p,q)”, Econometric Reviews, 37(8), 2018, 824-849.
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis