University of Economics, Prague
Advanced Statistical Methods
(Course Description)
Dr Nasrollah Saebi
()
April 2014,
Advanced Statistical Methods
(Course Description)
AIMS
· To introduce non-probabilistic algorithmic methods of forecasting.
· To introduce probabilistic Box-Jenkins methodology and ARIMA modelling from
which the future behaviour of a time series can be forecast.
LEARNING OUTCOMES
On successful completion of the course, students will be able to:
· Analyse time series and select appropriate forecasting techniques for them;
· suggest suitable non-probabilistic algorithmic models of forecasting to a time series data set;
· suggest tentative ARIMA models of forecasting using Box-Jenkins methodology to a non-seasonal time series data set;
· evaluate and critically assess the validity of the modelling outcomes from the computer output;
· use appropriate criteria to identify optimal model for forecasting using Box-Jenkins methodology.
CURRICULUM CONTENT
· Measures of forecasting errors and their uses.
· Method for data without a trend: Single Exponential Smoothing.
· Methods incorporating trend: Brown's method, Holt's Method.
· Method for seasonal data: Additive and Multiplicative Decomposition Methods involving centred moving averages and regression technique.
· The Box-Jenkins methodology: AR, MA and ARIMA models; the backshift operator; stationarity and invertibility. The Box-Jenkins modelling procedure. Akaike and Schwartz Bayesian model selection criteria.
· Use of appropriate industry standard software packages (e.g. SAS for Box-Jenkins modelling and forecasting methods and MS-Excel for other methods).
TEACHING AND LEARNING STRATEGY
The theoretical aspects will be delivered through a series of lectures, developing from the basic moving average methods. The lectures will be complemented by practical sessions in which time series data will be analysed. Tentative models are identified and forecasts are made using an appropriate statistical software package.
ASSESSMENT STRATEGY
Assessment consists of group modelling assignments. The group assignments are designed to assess understanding of students in selecting appropriate forecasting techniques and models, evaluating the validity of their models by interpreting the results from computer output, conducting relevant tests and making useful forecasts.
BIBLIOGRAPHY
Bowerman B L, O’Connell R T, and Koehler A B (2005), Forecasting,Time Series and Regression – An Applied Approach, Thomson
Box G E P & Jenkins G M, (1976), Time Series Analysis: Forecasting and Control, Holden-Day
Janacek G, (2001), Practical Time Series, Arnold
Maddala G S, (2001), Introduction to Econometrics, J Wiley & Sons
Makridakis S, Wheelwright S C & Hyndman R J, (1998), Forecasting: Methods and Applications, J Wiley & Sons
Madsen, H, (2008), Time Series Analysis, Chapman and Hall/CRC
Transferable Skills: In the normal course of study for this module a degree of competence in the following skills should be achieved:
Communication skills / Clear presentation of information, in a variety of visual forms (tables, diagrams, posters etc.).
Ability to present statistical concepts and derived inferences in an understandable form to non-scientists.
Working with others / Working constructively in a group, helping it to achieve its goals.
Respect for others opinions and beliefs.
Effectively interacting with staff and fellow students.
Planning / Planning and organising time effectively and efficiently to achieve objectives on time.
Problem solving / Using a variety of information sources.
Completing a project using a variety of skills and techniques.
PREPARED FOR: The University of Economics, Prague
Dr. Nasrollah Saebi
B.Sc. Economics (Special Subject: Statistics) (The London School of Economics and Political Science)
Ph.D. Statistics (London University)
Fellow of the Royal Statistical Society and Elected Member of The International Statistical Institute
Senior Lecturer in Statistics and Statistics Field Leader
Kingston University,
Faculty of Computing, Information Systems and Mathematics,
Penrhyn Road,
Surrey KT1 2EE, UK
email:
1