Dr John Thompson
“Truth, damned truth and statistics” – How statistics can help you get real value from your data
This is an introductory overview of the various roles of statistics, not only in analysing both quantitative and qualitative data but also in designing experiments, clinical diagnostics and therapeutics trials, device testing, evaluation and validation, sampling strategy, in reliability and maintainability engineering, in quality and process control, in audit, forensically, etc. John will talk about modern statistical tools and methods, including graphical ones, in a simple way with practical examples, comparing their strengths and weaknesses with those of conventional, classical methods. His approach is designed to be understandable by those with little or no experience of statistics. John will briefly and graphically illustrate his talk about the various tools and methods of statistics and how he has applied and developed these with practical examples from some of his previous work, for example:
- Developing methods for the HSE for exploring and analysing a large database of occupational exposures to dusts and toxic gases in the UK foundry industry over a 30yr period, including evaluating the effects of changes of exposure limits and their efficacy in different occupational practices in foundries.
- Developing methods of data smoothing and fitting for a radically new type of a prototype high sensitivity and very rapid response lung function test device.
- Evaluating reliability of haemodialysis equipment in a major West Midlands hospital, e.g., patterns of failures of equipment from different manufacturers over the full working life of such equipment to understand design flaws and the impact of user training or otherwise on failure patterns.
John is an entrepreneur, scientist, engineer and applied statistician who has worked in large and small industry, academia and the NHS. He has been involved in teaching, training, research and consultancy in applied statistics for 47 years, using it across a wide range of applications in medicine, industry, scientific and engineering R&D, quality/process control, environmental regulation, etc. He has over 70 peer reviewed publications, including five book chapters on applied statistics and chemometrics and a major HSE research report on statistical explorations of a large database of occupational exposures in the UK foundry industry. His areas of expertise include exploratory, robust, resistant and non-parametric statistics, statistical graphics, experimental design, statistical sampling strategy design, clinical diagnostics and therapeutics trial design and analysis, computer intensive resampling methods and, recently, compositional data modelling and analysis.
Email: email@example.com or firstname.lastname@example.org
Tel: 07787 552913