Distance MSc in Operational Research - Statistics

Credit Value: 12
Tutors: Tim Bedford and John Quigley

Aims and Objectives

You will be introduced to the basic theory and application of statistics. Topics covered included data analysis, probability theory, distributions and moments, estimation and hypothesis testing. In the second part of the course we aim to focus mainly on two areas - regression modelling and multivariate analysis. While key background theory will be presented, the emphasis is on the generation and interpretation of output from commercially available software. We aim to emphasise the use of statistical analysis to help support decision-making and the management of business and industrial problems. Cases will be used to illustrate topical issues.

By the end of the first part of the course you should be able to:

• analyse, describe, interpret and present the information contained in data sets;
• use commercially available software to compute and interpret appropriate statistics;
• use standard computational procedures to explore and interpret the information and structure contained in data sets.

Class aims

The aim of the course is to introduce statistical modelling. The first part of the course will focus on the foundations of statistical reasoning, while the second part will support the development of statistical modelling skills.

Learning outcomes

Subject specific knowledge and skills

• Display and interpret data using appropriate visual displays.
• Select, construct and interpret summary statistics.
• Understand probabilistic reasoning and compute probabilities for simple problems.
• Use appropriate empirical and probability distributions to model data.
• Use graphical methods to identify appropriate models and estimate parameters.
• Apply and interpret formal statistical estimation procedures and goodness-of-fit tests.

Cognitive abilities and non-subject specific skills

• Develop students ability to construct numerical argument
• Critical thinking with respect to quantitative analysis

Content/Structure of class

The class is taught in two parts. The first part is concerned with developing a solid grounding in the fundamental aspects of statistical reasoning and methods. Specifically the following topics will be covered:

• Visualising data
• Summarising data
• Calculus of probability
• Moments
• Probability distributions
• Estimation
• Hypothesis Testing
• Goodness-of-fit Tests

The second part builds on the material covered in the first part, first through the development of advanced statistical models and secondly through analysing complex multi-variate data sets. This class will be taught through exploring case studies to motivate statistical model during supervised computer lab sessions. Specifically the following topics will be covered:

• Simple linear regression modelling
• Multiple regression modelling
• Logistic regression
• Multivariate analysis
• Data mining techniques
  • Decision trees
  • Neural networks
  • Clustering

Resources

SPSS will be used extensively. This is provided by the University of Strathclyde.

Reading

Suggested for additional reading:

• Cox DR and Hinkley D (1974) Theoretical Statistics, Chapman and Hall.
• Draper NR and Smith H (1998) Applied Regression Analysis, Wiley Interscience.
• Flury B and Reidwyl H (1988) Multivariate Statistics : A Practical Approach, Chapman and Hall.
• Chapfield C (1995) Problem Solving - A Statisticans Guide, Chapman and Hall.

Assessment

One exam (50%) and an individual assignment (50%) in semester two.

Learning Outcomes

• Display and interpret data using appropriate visual displays.
• Select, construct and interpret summary statistics.
• Understand probabilistic reasoning and compute probabilities for simple problems.
• Use appropriate empirical and probability distributions to model data.
• Use graphical methods to identify appropriate models and estimate parameters.
• Apply and interpret formal statistical estimation procedures and goodness-of-fit tests.
• Construct and use models to explore inter-relationships over time and between variables.
• Develop a strategy for statistical modelling and analysis through problem solving.
• Use appropriate software tools to implement statistical analysis.

management science DEPARTMENT OF MANAGEMENT SCIENCE
UNIVERSITY OF STRATHCLYDE Graham Hills BUILDING 40 GEORGE STREET G1 1QE
t:0141 548 3613/3141 f:0141 552 6686
contact-mansci@strath.ac.uk