Nonparametric Bayesian Analysis of the Constant Stress Accelerated Life Test with Power Function Model

The linear accelerated model is often used to the statistical analysis of constant stress accelerated life test, whereas it does not relate well with the facts. By adopting the power functional accelerated model, the relationship of sample quantiles among different constant stress levels is obtained, which can lead to the estimations of the parameters in accelerated model and the characteristic coefficient vectors by virtue of the least square method, then the life-time data transformation between different stress levels can be operated. For complete data and censoring data, a Dirichlet process prior is introduced to gain the posterior distribution and the nonparametric Bayesian estimation of the reliability function, meanwhile, the consistency of the posterior estimators is proved. Finally, a real life example of Metal-Oxide-Semiconductor capacitors is analyzed to illustrate the effect of our model.