Markov switching GARCH models (MSGARCH)
Responsable du projet David Ardia
Collaborateur Keven Bluteau
Partenaire Kris Boudt
Résumé The goal of this project is to implement a package that will give the financial community tools to estimate, simulate, and test several MSGARCH models used in volatility (i.e., square root of conditional variance) forecasting. By relying on a hidden/latent variable, these models are able to switch among several processes for the conditional volatility and therefore, account for structural break in the volatility dynamics. MSGARCH have gained a huge interest in the financial risk management community over the recent years as they are better at forecasting volatility and provide more accurate risk measures. The package will follow the structure of rugarch since this is one of the most used packages for volatility modeling. The core will be implemented in C++ while simple R functions will facilitate usage of the package. Currently, no R package is available to estimate these models.
Page internet http://https://summerofcode.withgoogle.com/projects/?sp-s...
Type de projet Recherche appliquée
Domaine de recherche Financial econometrics, risk management
Source de financement Google Summer of Code
Etat Terminé
Début de projet 4-2016
Fin du projet 8-2016
Budget alloué 5,500 USD
Contact David Ardia