fEGarch - SM/LM EGARCH & GARCH, VaR/ES Backtesting & Dual LM Extensions
Implement and fit a variety of short-memory (SM) and
long-memory (LM) models from a very broad family of exponential
generalized autoregressive conditional heteroskedasticity
(EGARCH) models, such as a MEGARCH (modified EGARCH), FIEGARCH
(fractionally integrated EGARCH), FIMLog-GARCH (fractionally
integrated modulus Log-GARCH), and more. The FIMLog-GARCH as
part of the EGARCH family is discussed in Feng et al. (2023)
<https://econpapers.repec.org/paper/pdnciepap/156.htm>. For
convenience and the purpose of comparison, a variety of other
popular SM and LM GARCH-type models, like an APARCH model, a
fractionally integrated APARCH (FIAPARCH) model, standard GARCH
and fractionally integrated GARCH (FIGARCH) models, GJR-GARCH
and FIGJR-GARCH models, TGARCH and FITGARCH models, are
implemented as well as dual models with simultaneous modelling
of the mean, including dual long-memory models with a
fractionally integrated autoregressive moving average (FARIMA)
model in the mean and a long-memory model in the variance, and
semiparametric volatility model extensions. Parametric models
and parametric model parts are fitted through
quasi-maximum-likelihood estimation. Furthermore, common
forecasting and backtesting functions for value-at-risk (VaR)
and expected shortfall (ES) based on the package's models are
provided.
