Bayesian estimation and prediction for the transformed Wiener degradation process

摘要: This paper proposes some Bayesian inferential procedures for the transformed Wiener (TW) process, a new degradation process that has been recently suggested in literature to describe phenomena where increments are not necessarily positive and depend stochastically on current level. These have expressly conceived allow one incorporating into type of prior information, meaningful physical characteristics observed is generally available practical settings. Several different distributions proposed, each them reflecting specific degree knowledge phenomenon. Simple strategies eliciting hyper‐parameters from information provided. Estimates TW parameters functions thereof retrieved by adopting Monte Carlo Markov Chain technique. Procedures predicting increment, useful life unit, remaining used unit also Finally, an application developed basis set real measurements infrared light‐emitting diodes, widely communication systems. The obtained results demonstrate feasibility proposed approach flexibility process.