Econometrics of Energy Markets
This module covers the econometric modelling of energy returns, including univariate and multivariate time series and volatility models, and the estimation of Value at Risk for energy markets. Topics include stationary time series, univariate linear time series models, univariate and multivariate GARCH models, and approaches to modelling Value at Risk, with practical implementation in EViews and Python.
Delivery
This module consists of 2-hour lectures per day for 5 days, plus a 1-hour tutorial per day. During private study, students should strike a balance between reading the course material and the recommended textbook, and will also carry out applied exercises using the computer packages.
Study Hours
Approximately 100 hours of study, of which 15 are contact hours and 85 are private study.
Software Used
EViews, Python
Credits
10 CATS credits
Programme Faculty
Key Outcomes
- —The modelling of univariate and multivariate time series of energy returns
- —Practical time series modelling using EViews and Python
- —Nonlinear time series models, including volatility modelling and the score-driven approach
- —Forecasting energy price volatilities and correlation
- —Forecasting Value at Risk for energy markets
Desired Skills
- —Understand the nature of time series models and the way they are applied in practice
- —Present, interpret and analyse information and results from EViews and Python
Lecture Programme
- WK 01
Lecture 1: Stationary time series
- ·Review of the basic concepts of stationary time series
- ·Stylized fact of energy returns
- ·Short and Long memory dependence in returns time series
- WK 02
Lecture 2: Univariate Linear Time series models of energy returns
- ·ARIMA models
- ·Structural time series models
- ·Estimating ARIMA models in EViews and Python
- WK 03
Lecture 3: Univariate GARCH models of energy returns
- ·Short memory GARCH: estimation and testing
- ·Long memory GARCH: estimation and testing
- ·Forecasting energy returns with GARCH models
- WK 04
Lecture 4: Multivariate GARCH models
- ·CCC, DCC, BEKK models
- ·Estimation of MGARCH models in Python
- WK 05
Lecture 5: Modelling the Value at Risk
- ·Historical approach
- ·Parametric approach
Assessment
Online coursework submission with the support of your module lecturer and tutor. All sessions are conducted live online at a scheduled time and recorded for review.