7th SIPTA Summer School

Home

Are you interested in modelling severe uncertainty in your applications? Are you worried about the impact of the choice of prior in your Bayesian analysis? Are you interested in prior-data conflict and/or missing data? Do you want to learn how imprecise probability can help you making robust decisions under uncertainty? Then the SIPTA summer school is for you!

Important dates

• Registration deadline: Friday 24 June 2016, or until places run out
• School: Monday 29 August – Friday 2 September 2016

About the school

Often, uncertainty is modelled by a probability distribution, and treated using techniques from probability theory. However, when information is scarce, vague, or conflicting, a unique probability distribution may be hard to identify. In that case, imprecise probability aims to represent the really available knowledge, and provides tools to model and work with weaker states of information. It includes both qualitative models (comparative probability, partial preference orderings, etc.) and quantitative models (interval-valued probabilities, convex sets of probability measures, upper and lower previsions, belief functions, possibility measures, etc.).

The Society for Imprecise Probability: Theories and Applications, or SIPTA, aims at promoting research on imprecise probability. This is done through a series of activities including ISIPTA conferences every odd year since 1999, and SIPTA schools every even year since 2004.

The aim of SIPTA schools is to introduce interested students and researchers to the basics of imprecise probability topics, both theoretical and applied. Leading specialists in different aspects of imprecise probabilities lecture on the main concepts and techniques associated to their area of expertise, in a friendly environment favouring interaction between participants. An important part of the time is devoted to hands-on exercises involving applied problems in e.g. engineering and environmental risk assessment.

The SIPTA school 2016 will take place in the Department of Mathematical Sciences, Durham University, United Kingdom, from Monday 29 August until Friday 2 September.

On the first day of the school, the students will have the opportunity to briefly present their own work.

The last day of the school overlaps with the WPMSIIP workshop, and will give all participants the possibility to interact with the wider imprecise community.

A basic understanding of probability and calculus are required (first year university level). A knowledge of Bayesian statistics is an advantage but is not required.

Lecturers

• Edoardo Patelli, Institute for Risk and Uncertainty, University of Liverpool, UK. Research activities focus on the general area of risk analysis and uncertainty quantification and robust design of safety critical systems. Current researches deal with the development of generalised probabilistic methods, efficient Monte Carlo simulation approaches and their scalability on High Performance Computing facilities for the analyses of large and complex problems within feasible computational times.

• Ullrika Sahlin, Centre of Environmental and Climate Research, Lund University, Sweden. My research focuses on the quantification of uncertainty in environmental impact assessments and evidence synthesis to support robust decision making. I use case studies such as the integration of empirical evidence into risk assessment models for conservation or ecosystem service provisions, invasive species management and chemical safety assessment. I see robust Bayesian analysis as a way to consider unreliable knowledge and seek solutions to get this to work in practical risk assessments.

• Gero Walter, Department of Industrial Engineering & Innovation Sciences, Eindhoven University of Technology, The Netherlands. My research focuses on prior-data conflict situations, i.e. when information from data is in conflict with prior assumptions.

• Matthias Troffaes, Department of Mathematical Sciences, Durham University, UK. My research focuses on modelling of severe uncertainty, risk, and decision making, with applications in engineering and environmental sciences.

Organizing Committee

• Matthias Troffaes (Durham University, UK)
• Gert de Cooman (Gent University, Belgium)
• Olivier Strauss (University of Montpellier, France)
• Andrea Wiencierz (York University, UK)

We also thank Frank Coolen (Durham University, UK) for his contributions to the organisation of the school.

For practical questions about the school, please contact Matthias Troffaes.