Department of Mathematical Sciences, Unit Catalogue 2008/09 |
MA50085 Time series |
| Credits: 6 |
| Level: Masters |
| Semester: 2 |
| Assessment: CW 25%, EX 75% |
| Requisites: |
|
Aims & Learning Objectives: Aims: To introduce a variety of statistical models for time series and cover the main methods for analysing these models. To facilitate an in-depth understanding of the topic. Objectives: At the end of the course, the student should be able to: * Compute and interpret a correlogram and a sample spectrum; * derive the properties of ARIMA and state-space models; * choose an appropriate ARIMA model for a given set of data and fit the model using an appropriate package; * compute forecasts for a variety of linear methods and models; * demonstrate an in-depth understanding of the topic. Content: Introduction: Examples, simple descriptive techniques, trend, seasonality, the correlogram. Probability models for time series: Stationarity; moving average (MA), autoregressive (AR), ARMA and ARIMA models. Estimating the autocorrelation function and fitting ARIMA models. Forecasting: Exponential smoothing, Forecasting from ARIMA models. Stationary processes in the frequency domain: The spectral density function, the periodogram, spectral analysis. State-space models: Dynamic linear models and the Kalman filter. |