This module is to introduce students to a range of modelling strategies for time series analysis and forecasting, with a focus on practical applications as well as theoretical concepts. Throughout the module, students will explore issues related to model building, accurate prediction, and evaluating economic and financial markets. By the end of the module, students should be able to: (1) understand the nature of variable dependence over time, including trends and seasonality; (2) describe and model the dynamic relationships using univariate and multivariate analyses; and (3) generate appropriate forecasts while also characterizing the uncertainty in these forecasts.
Topics covered in this module may include (but are not limited to): stationary and non-stationary time series models, serial correlation, unit root and cointegration, error correction, forecasting and regression analysis of time series data, AR, MA, ARDL, ARIMA, GARCH and stochastic volatility modelling.
Learning Outcomes
By the end of the module students should be able to:
Describe and summarise the empirical properties of time series data.
Develop and fit a range of quantitative, statistical time series models.
Forecast future observations of the time series.
Build and apply programs in R or other software for the analysis and forecast of time series data.
Assessment
Assessment Methods & Exceptions
Assessment:
1.5 hours 80% examination, 20% coursework problem sheets.
