Unit name | Advanced Time Series |
---|---|
Unit code | MATHM6003 |
Credit points | 10 |
Level of study | M/7 |
Teaching block(s) |
Teaching Block 2C (weeks 13 - 18) |
Unit director | Professor. Nason |
Open unit status | Not open |
Pre-requisites |
None |
Co-requisites |
None |
School/department | School of Mathematics |
Faculty | Faculty of Science |
Time series are measurements on variables collected over time. The focus of this course will be on the analysis and forecasting of financial time series, by which we mean, for example, stock indices, share prices or currency exchange rates, amongst others. Of great interest to market practitioners and theoretical statisticians alike is the ability to understand the structure and forecast time series of this type. To do this, usually a probabilistic model is required. This course will introduce two families of models designed to handle financial time series: stationary nonlinear models, and locally stationary linear models.
Aims
Syllabus
Harmonization from stationarity assumptions. Examples of time-varying conditional variance. The ARCH model. The GARCH model. Estimation and model fitting. Cointegration. Locally stationarity. Locally stationary Fourier processes. Locally stationary wavelet processes. Evolutionary wavelet spectrum. Localized autocovariance. Spectral estimation.
Relation to Other Units
This course builds on MATH33800, Time Series Analysis.
At the end of the unit students should be able to:
Transferable Skills:
The students will gain experience of modelling and fitting advanced time series models to data. These skills are highly valued in a number of areas but especially financial data modelling.
Lectures (with encouraged audience participation) plus problem and solution sheets. Some of the questions on the problem sheets will be to do with practical data analysis.
The final assessment mark for the unit is calculated from a 1½-hour written examination in APRIL. The exam will have THREE questions. A candidate's best TWO answers will be used for assessment. Calculators of an approved type (non-programmable, no text facility) may be used.