06/04/2018 - Bayesian inference for the multiple step-stress accelerated test under censored data - Palestrante: Fernando A. Moala (UNESP)

Seminário Conjunto UFSCar/ICMC - 06/04/2018 (sexta-feira) – 14h00

LOCAL: Sala 43 do DEs-UFSCar

PALESTRANTE: Fernando A. Moala, São Paulo State University (UNESP), Presidente Prudente, Brazil
Department of Statistics

TÍTULO: Bayesian inference for the multiple step-stress accelerated test under censored data

RESUMO: This work presents the multiple step-stress accele rated life test for the cumulative exposure model using complete and censored data. As suming that the lifetimes of test item follow the Weibull or gamma distributions, the maximum likelihood estimation and Bayesian approaches are used to estimate the distribution parameters. Some objective and subjective priors are investigated and compared under symmetric and assymetric loss functions such as squared, linex and general entrop y loss functions. It is considered Type II censoring scheme and progressive type-II censoring with random removals. A sensitivity analysis of these Bayesian and maximum likelihood estimators are also presented by simulation Monte Carlo study, and a data set is analyzed for illustrative purposes.


Contamos com a presença de todos!