Bayesian analysis for Cox\u27s proportional hazard model with error effect and applications to Accelerated Life Testing data

In this thesis we investigate Bayesian analysis for Cox\u27s proportional hazard model with error effect on the study of Accelerated Life Testing. We make statistical inference under Bayesian methods by using the well known Markov chain Monte Carlo(MCMC) techniques to estimate the parameters involved in the model and predict reliability (or survival) in accelerated life testing. We apply this method to the analysis of the knock sensor failure data (knocking vibration from the cylinder block is sensed as vibrational pressure by the Knock Sensor), in which some observations in the data are censored. The study was realized on Delphi Design Center located in Juarez, Mexico. The failure times at a constant stress level are assumed to be from a Weibull distribution. The analysis of the data from ALT will be made for the posterior estimation of parameters and prediction of survival function as well as the comparisons with the classical results from the Arrhenius model