Bayes inference for a non-homogeneous Poisson process with power intensity law (reliability)

摘要: Monte Carlo simulation is used to assess the statistical properties of some Bayes procedures in situations where only a few data on system governed by NHPP (nonhomogeneous Poisson process) can be collected and there little or imprecise prior information available. In particular, case failure truncated data, two are analyzed. The first uses uniform PDF (probability distribution function) for power law noninformative alpha , while other assuming an informative scale parameter obtained using gamma knowledge mean number failures given time interval. For both cases, point interval estimation discussed. Comparisons with corresponding maximum-likelihood estimates sample sizes 5 10. computationally much more onerous than ones, since they general require numerical integration. small sizes, however, their use may justified exceptionally favorable shown when compared classical ones. robustness respect wrong assumption beta interesting. >