F71DA Data Analytics and Time Series Analysis

Dr Fraser Daly

Course co-ordinator(s): Dr Fraser Daly (Edinburgh).

Aims:

This course aims to provide a good understanding of the concepts and methods used in time series analysis and advanced techniques for data analytics.

Detailed Information

Course Description: Link to Official Course Descriptor.

Pre-requisites: none.

Location: Edinburgh.

Semester: 2.

Syllabus:

• Basic time series concepts and operators
• Stationary processes, general linear filter, autocorrelation function and spectrum
• MA, AR and ARMA processes
• ARIMA processes and Random Walk (RW) with or without drift
• Model estimation and model selection
• Models with trend and/or seasonality
• Forecasting
• Introduction to nonlinear processes
• Elementary principles of machine learning
• Copulas
• Extreme value theory

Learning Outcomes: Subject Mastery

On completion of this course the student should be able to:
• demonstrate knowledge of, and a critical understanding of, the main concepts of time series analysis
• demonstrate knowledge of, and a critical understanding of, the main properties of MA, AR, ARMA, ARIMA, and RW models
• use least squares, maximum likelihood and other methods to fit time series models to the data
• select proper model(s) using e.g. AIC or BIC
• fit trend and seasonal trend to the data, and fit time series models to the residuals
• understand methods used to produce forecasts
• understand ARCH, GARCH and other nonlinear time series models and their applications for modelling of financial data
• understand time series data well, and perform basic calculations and summaries of time series data
• understand and critically assess time series models fitted by computer packages
• use a range of time series models to produce forecasts
• understand the elementary principles of machine learning
• apply copulas to multivariate data
• understand the basic concepts of extreme value theory

Learning Outcomes: Personal Abilities

At the end of the course student should be able to:

• Demonstrate the ability to learn independently
• Manage time, work to deadlines and prioritise workloads
• communicate meaningfully and productively with others (including practitioners and professionals in the financial services industry) on data analytics issues
• use statistical software to fit time series models to data and
• analyse empirical data using modern data analytics techniques

Assessment Methods:

Assessment: Examination: (weighting – 70%) Coursework: (weighting – 30%)
Re-assessment:  Examination: (weighting – 100%)

Re-assessment in next academic year

SCQF Level: 11.

Credits: 15.

Other Information

Help: If you have any problems or questions regarding the course, you are encouraged to contact the lecturer

VISION: further information and course materials are available on VISION