|
| Module Availability |
Autumn |
|
|
| Assessment Pattern |
|
Unit(s) of Assessment
|
Weighting Towards Module Mark( %)
|
|
2 hour unseen examination
|
56%
|
|
2 piece of coursework
|
34%
|
|
1 class test or coursework
|
10%
|
|
Qualifying Condition(s)
A weighted aggregate mark of 40% is required to pass the module.
|
|
|
|
| Module Overview |
This module covers some areas of statistics that are relevant to business and management. Much financial data, such as monthly unemployment figures, FTSE index, arrives in the form of Time Series and modelling such data and prediction of future values is vital. this module, issues relating to modelling and forecasting. These issues are approached theoretically in lectures and practically in lab sessions with the investigation of real life data sets.
The module also includes one of the following:
(i) An introduction to Bayesian decision theory with applications to business problems; (2010/11)
(ii) A selection of more advanced topics in time series including strategy for selecting ARIMA models.
The statistical package R is used for practical work. The emphasis in the lab sessions is on understanding the data and forecasting future observations. |
|
|
| Prerequisites/Co-requisites |
| MAT2002 General Linear Models |
|
|
| Module Aims |
| The aim is to introduce fundamental concepts in univariate Time Series and to teach basic techniques used in dealing with data arising from such a Time Series along with more advanced topics in time series or decision theory. The course provides students with the tools to analyse and interpret analyses of data arising from Time Series, to forecast future values and to analyse decision problems. |
|
|
| Learning Outcomes |
At the end of the module a student should:
(1)be familiar with the main results and methods of univariate time series/decision analysis;
(2)be able to apply these results to analyse appropriate data;
(3)be able to interpret the results from such analyses. |
|
|
| Module Content |
1. Time series and forecasting: Linear filters, differencing and exponential smoothing. The Box-Jenkins approach, introduction to autoregressive and moving average models. Applications and business finance.
One or other of the following topics will be covered in the remainder of the course.
2. Bayesian decision theory. Decision trees for simple and business problems. Subjective probability and utility. Utility of money. Consistency and coherence. Scoring rules. Utility functions. Risk aversion. Multi-attribute utility. Group decision making. Sensitivity analysis.
3. Building strategy for ARIMA models. Autocorrelation and partial autocorrelation functions. Trend function, steady and linear growth models. Business and finance case studies including: stock price deviations, monthly temperatures, kilometres flown by airlines.
|
|
|
| Methods of Teaching/Learning |
| 3 contact hours per week for 10 weeks. Mainly lectures but including some supervised computer lab sessions. |
|
|
| Selected Texts/Journals |
D. C. Montgomery, C. L. Jennings, M. Kulahci, Introduction to Time Series Analysis and Forecasting. Wiley, (2008).
C. Chatfield, The Analysis of Time Series: An introduction. (6th ed.), Chapman & Hall, (2004).
G.E.P. Box, G.M. Jenkins, and G.C. Reinsel, Time series analysis: Forecasting and Control. (3rd ed.), Holden Day, (1994).
M.J. Crawley, Statistics: An Introduction using R. Wiley, (2005).
W.N. Venables and B. D. Ripley, Modern Applied Statistics with S-PLUS, Springer, (1999).
J.D. Cryer, Time Series Analysis. Duxbury Press, (1986).
P. Brockwell and R. Davis, An introduction to Time Series and Forecasting. (2nd ed.) (2002).
Lindley, D.V. Making Decisions.
Smith, J.Q. Decision Analysis: A Bayesian approach.
French,
S. Readings in Decision Analysis |
|
|
| Last Updated |
March 2011 |
|
