Econometric Institute and Princeton University Pressorganize the intensive PhD-course:
"Multivariate Volatility Modelling with Dynamic Correlations"
Prof. R.F. Engle (Stern School of Business, New York University)
May 21-23, 2003
Erasmus University Rotterdam
Course Outline
1. Introduction to volatility modelling and univariate GARCH models (van Dijk)
- Univariate GARCH and stochastic volatility models
- Testing for GARCH effects
- Estimation, diagnostic checking, forecasting
2. Introduction to multivariate GARCH models (Engle)
- Survey of the multivariate GARCH literature
- Introduction of the Dynamic Conditional Correlation (DCC) model
- Specifications allowing downside risk
3. The Econometrics of the DCC Estimator (Engle)
- Standard errors
- Variance targeting
- Diagnostic testing
- Monte Carlo evidence
- Empirical results
4. Alternative models for time-varying correlations (Martens)
- Sample covariances matrix with equal or exponentially declining weigths
- Factor models, including estimating the factor returns using a Principal Component Analysis, using observable factors, and using observable factor exposures to estimate unobservable factor returns.
- Theoretical (dis)advantages of eacht model and empirical comparisons
5. A Factor Model (Engle)
- Formulation of factor model with unobservable factor returns
- Attribute of individual assets
- Empirical results
- Applications to portfolio construction and dynamic hedging