Bayesian analysis of incomplete time and cause of failure data

For series systems with k components it is assumed that the cause of failure is known to belong to one of the 2(k) - 1 possible subsets of the failure-modes. The theoretical time to failure due to k causes are assumed to have independent Weibull distributions with equal shape parameters. After finding the MLEs and the observed information matrix of (lambda(1), ..., lambda(k), beta), a prior distribution is proposed for (lambda(1),..., lambda(k)), which is shown to yield a scale-invariant noninformative prior as well. No particular structure is imposed on the prior of beta. Methods to obtain the marginal posterior distributions of the parameters and other parametric functions of interest and their Bayesian point and interval estimates are discussed. The developed techniques are illustrated using a numerical example.