Volatility Modeling
From univariate GARCH to rough volatility and multivariate models
This module provides a comprehensive treatment of volatility modeling in financial markets, progressing from classical univariate specifications through realized measures, stochastic and rough volatility models, and multivariate extensions.
Sessions¶
| # | Topic | Key Concepts |
|---|---|---|
| 1 | Foundations and Stylized Facts | Volatility clustering, fat tails, leverage effect, long memory |
| 2 | ARCH and GARCH Models | Engle’s ARCH, Bollerslev’s GARCH, estimation, diagnostics |
| 3 | Asymmetric GARCH | GJR-GARCH, EGARCH, TARCH, leverage effects in volatility |
| 4 | Advanced Univariate Models | FIGARCH, APARCH, component models, long memory |
| 5 | Realized Volatility | High-frequency data, realized variance, microstructure noise |
| 6 | HAR Models | Heterogeneous Autoregressive model, forecasting realized volatility |
| 7 | Stochastic Volatility | Heston model, latent volatility, estimation challenges |
| 8 | Rough Volatility | Fractional Brownian motion, rough Heston, rBergomi |
| 9 | Multivariate Volatility | DCC, BEKK, CCC, factor models, spillover analysis |
| 10 | Path-Dependent Applications | Variance swaps, volatility trading, risk management |
How to use these notebooks¶
The course is designed sequentially. Early sessions build the classical GARCH toolkit, middle sessions introduce non-parametric and continuous-time approaches, and the final sessions cover multivariate and applied topics. Each notebook combines mathematical derivations with Python implementations.