Decision Making in Reliability

Distribution-free methods are evolved for 4 models of evaluating time-to-failure. Two decision procedures for choosing the better of two equipments are given in models I & II. Decision procedures for whether two equipments have the same availability or reliability are given in models III & IV; in these models, it is assumed that the mission time is a r.v. in the interval (0, T0). The method of model I is superior to existing tests like the Wilcoxon-Rank-Sum test and Mann-Whitney test in a particular case. Model II is based on the time taken to return to the initial state by a Markov chain and is optimum for large sample sizes. In model III, even though the distributions of time to failure and time to repair-completion are negative exponential, the method is general, distribution-free and optimal. Hence the type I error is constant even if the distributions of time to failure and repair-completion differ from the assumed distributions. Model IV is also distribution-free and optimum.