نوع مقاله : مقاله پژوهشی
1 گروه مکانیک - دانشکده مهندسی - دانشگاه پیام نور
2 عضو هیئت علمی دانشگاه آزاد لاهیجان
عنوان مقاله [English]
The accelerated life test model is one of the optimal models to obtain information about the reliability of the industrial products in the shortest possible time. In this article, the problem of the Bayesian prediction intervals from the Kumaraswamy distribution based on censored data in constant-stress partially accelerated life test model is studied. Since the Bayesian predictive function can not be computed in closed-form, the Markov chain Monte Carlo algorithm is used to construct the prediction intervals. Simulation and real data analyses are performed to compare different Bayesian prediction intervals. The results show that the prediction intervals perform well and contain the actual values of the data. The obtained results can be used to increase the quality and reduce the time and cost of product quality control tests.