Picture of a sphere with binary code

Making Strathclyde research discoverable to the world...

The Strathprints institutional repository is a digital archive of University of Strathclyde research outputs. It exposes Strathclyde's world leading Open Access research to many of the world's leading resource discovery tools, and from there onto the screens of researchers around the world.

Explore Strathclyde Open Access research content

Applying Bayes linear methods to support reliability procurement decisions

Bedford, Tim and Denning, Richard and Revie, Matthew and Walls, Lesley and , IEEE (2008) Applying Bayes linear methods to support reliability procurement decisions. In: UNSPECIFIED.

Full text not available in this repository. (Request a copy from the Strathclyde author)

Abstract

Based on the prior belief stated by the decision maker and the observations made, the contractor, at this stage, has not given the decision maker sufficient evidence to suggest they are meeting all four reliability requirements. The model indicates the expectation of Vehicle B's basic reliability is greater than the target. However, the expectation of both of Vehicle A's reliability requirements and Vehicle B's mission requirement is lower than the target. In the case of Vehicle A, the probability of meeting the target is small. Extensive sensitivity analysis has been carried out to investigate whether or not the three reliability requirements currently not being met could be met given changes in the prior specification by the decision maker. Two scenarios of particular interest were investigated; first, what changes could be made to the prior expectation so that requirements are being met, and second, what changes could be made to the covariance structure in order that reliability requirements were met. For the three reliability requirements currently not met, the decision maker did not believe it was feasible to modify his prior belief structure to such an extent that the adjusted expectation of each of the three requirements was greater than the target.