Picture of a black hole

Strathclyde Open Access research that creates ripples...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of research papers by University of Strathclyde researchers, including by Strathclyde physicists involved in observing gravitational waves and black hole mergers as part of the Laser Interferometer Gravitational-Wave Observatory (LIGO) - but also other internationally significant research from the Department of Physics. Discover why Strathclyde's physics research is making ripples...

Strathprints also exposes world leading research from the Faculties of Science, Engineering, Humanities & Social Sciences, and from the Strathclyde Business School.

Discover more...

Applying Bayes linear methods to support reliability procurement decisions

Bedford, Tim and Denning, Richard and Revie, Matthew and Walls, Lesley (2008) Applying Bayes linear methods to support reliability procurement decisions. In: Annual Reliability and Maintainability symposium, 2008-01-28 - 2008-01-31.

This is the latest version of this item.

[img]
Preview
PDF (strathprints007452.pdf)
strathprints007452.pdf

Download (207kB) | Preview

Abstract

Bayesian methods are common in reliability and risk assessment, however, such methods often demand a large amount of specification and can be computationally intensive. Because of this, many practitioners are unable to take advantage of many of the benefits found in a Bayesian-based approach. The Bayes linear methodology is similar in spirit to a Bayesian approach but offers an alternative method of making inferences. Bayes linear methods are based on the use of expected values rather than probabilities, and updating is carried out by linear adjustment rather than by Bayes Theorem. The foundations of the method are very strong, based as they are in work of De Finetti and developed further by Goldstein. A Bayes linear model requires less specification than a corresponding probability model and for a given amount of model building effort, one can model a more complex situation quicker. The Bayes linear methodology has the potential to allow us to build ''broad-brush' models that enable us, for example, to explore different test setups or analysis methods and assess the benefits that they can give. The output a Bayes linear model is viewed as an approximation to 'traditional' probabilistic models. The methodology has been applied to support reliability decision making within a current United Kingdom Ministry of Defence (MOD) procurement project. The reliability decision maker had to assess different contractor bids and assess the reliability merit of each bid. Currently the MOD assess reliability programmes subjectively using expert knowledge - for a number of reasons, a quantitative method of assessment in some projects is desirable. The Bayes linear methodology was used to support the decision maker in quantifying his assessment of the reliability of each contractor's bid and determining the effectiveness of each contractor's reliability programme. From this, the decision maker was able to communicate to the project leader and contractors, why a specific contractor was chosen. The methodology has been used in other MOD projects and is considered by those within the MOD as a useful tool to support decision making. The paper will contain the following. The paper will introduce the Bayes linear methodology and briefly discuss some of the philosophical implications of adopting a Bayes linear methodology within the context of a reliability programme analysis. The paper will briefly introduce the reliability domain and the reasons why it is believed that the Bayes linear methodology can offer support to decision makers. An in-depth analysis of the problem will then be given documenting the steps taken in the project and how future decision makers can apply the methodology. A brief summary will then be given as to possible future work for those interested in the Bayes linear methodology.

Available Versions of this Item