Financial Time Series and Forecasting

Overview

Time series and statistical modelling is a fundamental component of the theory and practice of modern financial asset pricing as well as financial risk measurement and management. Further, forecasting is a required component of financial and investment decision making. This unit provides an introduction to the time series models used for the analysis of data arising in financial markets. It then considers methods for forecasting, testing and sensitivity analyses, in the context of these models. Topics include: the properties of financial return data; the Capital Asset Pricing Model (CAPM); financial return factor models, with known and unknown factors, in panel data settings; modelling and forecasting conditional volatility, via ARCH and GARCH; forecasting market risk measures such as Value at Risk. Emphasis is placed on applications involving the analysis of many real market datasets. Students are encouraged to undertake hands-on analysis using an appropriate computing package.

Topic 1: Introduction to Python and financial return data

Topic 2: Regression review and the CAPM and multi-factor models

Topic 3: Regression, CAPM, and factor models (ctd)

Topic 4: Forecasting, forecast accuracy, and introduction to time series

Topic 5: Time series (ctd), AR, and MA models

Topic 6: Forecasting with ARMA models and intro to volatility modelling

Topic 7: ARCH and GARCH volatility modelling

Topic 8: GARCH (ctd), risk metrics, and volatility asymmetry

Topic 9: Volatility forecasting and volatility proxies

Topic 10: Financial risk and its measurement

Topic 11: Forecasting value at risk (VaR)

Topic 12: Forecasting tail risk, VaR, and expected shortfall (ES)