Design and Analysis of Experiments
To be scheduled
This course covers the principles and practice of designing experiments, and the analysis of data from them. The course covers the following topics:
- choice of experimental units;
- importance of randomisation, and the practicalities;
- replication and sample size;
- blocking and matching;
- commonly used designs, including completely randomised designs, randomised block and matched pair designs, Latin square designs;
- treatments, including factorial structures;
- analysis of data from designed experiments;
- analysis of variance and covariance;
- special designs, including incomplete block designs, split-plot designs, and fractional factorial designs;
- transformations of data;
- practical and ethical issues arising in the conduct of experiments.
The presenter is Associate Professor Graham Hepworth, Consultant for the Statistical Consulting Centre and Senior Lecturer in the Department of Mathematics & Statistics. Graham has had extensive experience over two decades in design and analysis of experiments, in fields such as forestry, horticultural science, animal studies, medicine and the social sciences.
The four days are deliberately arranged so that there is a weekend break during the course. Each day will consist of four approximately equal-length sessions; the first session of the day will commence at 9:00 a.m. and the final session will end at approximately 4:45 p.m. The sessions will mix lecture presentations with practical work.
All participants have access to a PC. The statistical package Minitab (release 16 for Windows) will be used in the course. However, the course will not be package-centred, and no prior experience with Minitab is necessary.
The course is one of the specialised courses offered by the Statistical Consulting Centre. Generally, the Centre offers the introductory course "Statistics for Research Workers" at least twice, and at least one additional, more specialised course. The last occasion that Design and Analysis of Experiments was run was in 2015.
Who should take this course?
The course is suitable for researchers involved in the design and analysis of research on the effectiveness of interventions or treatments. Applications include randomised trials in medicine or the social sciences, designed experiments in the biological sciences, studies of processes in engineering, as well as many other possibilities in other disciplines.
Participants should have some understanding of statistics at an introductory level. For example, participants should know about hypothesis tests and confidence intervals, and, preferably, analysis of variance. The course "Statistics for Research Workers" would be suitable preparation.
Cost and enrollment details:
Full Cost $1100 (incl. $100 GST).
The University of Melbourne graduate researcher student $880
(incl. $80 GST, GST does not apply if paying through your University school.)
$30 Cancellation fee applies
The fee includes a comprehensive set of notes, and morning and afternoon tea. Lunches are not provide.
Giblin Eunson Library
111 Barry Street
T: +61 3 8344 6995
$30 cancellation fee applies