A methodology for sensitivity analysis of maintenance and reliability models

Baker presented a methodology for sensitivity analysis of models that had been fitted to data by statistical methods, e.g. likelihood-based methods, and where the purpose of modelling was to calculate a cost function or loss function. Use of this methodology is envisaged as a quick way to get insight into how to further refine a model, and into which additional data to collect. It is essentially an exploratory method that would precede use of any more formal decision-theoretic methods. The field of maintenance and reliability offers a rich field for application of the method. The methodology is briefly summarized and is illustrated with two examples drawn from this field. A simulation study using a three-parameter model of maintenance is then used to exemplify the accuracy of the method as a function of sample size.