Optimising the design of experiments is an important consideration in many areas of science (e.g. in biology, chemical engineering, clinical trials, and epidemiology). The theory of optimal experimental design is a statistical tool that allows us to determine the optimal experimental protocol to gain the most information about model parameters, subject to constraints on available resources.
The aim of this project is to determine the optimal experimental design for group dose-response challenge experiments. A group dose-response challenge experiment is an experiment in which we expose subjects to a range of doses of some infectious agent, bacteria or drug, and measure the number of individuals that become infectious at each dose. These experiments are used to obtain a range of statistics of interest, for example, to food production companies and the World Health Organization. These statistics are used to assess and monitor safe levels of certain bacteria or infectious agents, that may be present in livestock. We wish to contain the bacteria or infectious agent in the livestock to be within a safe level, in order to reduce the chance of spreading the infection to humans when livestock are used for human consumption. In particular, we consider the spread of the bacteria Campylobacter jejuni amongst chickens. C. jejuni is well recognised as one of the most common causes of enteric (intestinal) disease in humans (e.g., gastro-enteritis). In general, the Campylobacter genus of bacteria are the most common cause of food borne diarrhoeal disease in the developed world — surpassing Salmonella and Shigella spp. — with the C. jejuni species being the most common cause.
By determining the optimal experimental designs for these group dose-response challenge experiments, we aim to provide researchers with the necessary tools to perform the best possible experiment, in order to gain the most information on the characteristics of their infectious agent, bacteria or drug of interest.
Associated staff: Student — David Price; Others — Prof. Nigel Bean & Dr Jono Tuke