Unit information: Experimental Design in 2013/14

Please note: you are viewing unit and programme information for a past academic year. Please see the current academic year for up to date information.

Unit name Experimental Design
Unit code MATH35120
Credit points 10
Level of study H/6
Teaching block(s) Teaching Block 2D (weeks 19 - 24)
Unit director Dr. Didelez
Open unit status Not open
Pre-requisites

MATH35110
Co-requisites

None
School/department School of Mathematics
Faculty Faculty of Science

Description including Unit Aims

The design of an experiment is crucial in determining what questions can be answered from statistical analysis of data from that experiment. Experimental design originated in an agricultural context but is now important in very many application areas. We will discuss general aspects of experimental design from theory to construction, giving practical examples from the areas of agriculture/biology, medical research and quality control techniques in industry.

Unit Aims

To gain an understanding of the key features of experimental design from theory, through construction, to application.

Syllabus

  • Introduction to the importance of designing experiments; basic terminology
  • Replication, randomisation and local control (including completely randomised and randomised complete block designs)
  • More complex orthogonal designs (Latin squares, Graeco-Latin squares, incomplete block designs)
  • Factorial treatment structures; fractional factorials, confounding, split plot designs
  • Quantitative factors and response surfaces
  • Detailed case studies

Intended Learning Outcomes

By the end of the unit the student should have a good working understanding of:

  • the importance of good experimental design
  • the theory and construction of a range of widely used study designs

criteria to use in selection of appropriate designs in a wide range of application areas

  • relevance of design to subsequent data analysis

Teaching Information

Lectures (including both theory and illustrative applications), supported by exercise.

Assessment Information

The assessment mark for Experimental Design is calculated from a 1½-hour written examination consisting of THREE questions. A candidate's best TWO answers will be used for assessment. Calculators of an approved type (non-programmable, no text facility) are allowed. Statistical tables will be provided.

Reading and References

Any of the following texts will cover all or most of the course contents; the first is the most basic, the second and third more detailed but from differing perspectives.

Clarke, G.M. and Kempson, R.E. (1997) Introduction to the design and analysis of experiments, Arnold.

Mead, R. (1988) Design of experiments: statistical principles for practical applications, CUP.

Cox, D.R. and Reid, N. (2000) The theory of the design of experiments, CRC.

The following texts also contain much useful information on specific aspects of the subject:

Logothetis, N & Wynn, H. P. (1989). Quality through design: experimental design, off-line quality control and Taguchi's contribution, OUP.

Cochran, W. & Cox, G. (1957) Experimental design, Wiley.

Related links