In this paper, inference for a competing risks model is studied when latent failure times follow Kumaraswamy distribution and causes of failure are partially observed. Under generalized progressive hybrid censoring, existence and uniqueness of maximum likelihood estimators of model parameters are established. The confidence intervals are obtained by using asymptotic distribution theory. We further compute Bayes estimators along with credible intervals. In addition, inference is also discussed when there is order restricted shape parameters. The performance of all estimates is investigated using Monte-Carlo simulations. Finally, analysis of a real data set is presented for illustration purposes.
16 August 2020 in Journal of Statistical Theory and Practice
In this article, estimation problems for the Burr X distribution under a progressive-stress accelerated life test with progressive type-II censoring are studied. The stress is assumed to be a linearly increasing function of time. The inverse power law and the cumulative exposure model are considered. The classical and Bayesian estimations for the model parameters are obtained by using maximum likelihood method and Markov chain Monte Carlo technique,respectively. The asymptotic confidence intervals are constructed and highest posterior density intervals are also established. A simulation study is conducted to investigate the performance of the proposed point and interval estimations. Finally, a real data set is analysed for illustration.
13 June 2022 in Quality Technology & Quantitative Management
We study a competing risks model under the assumption that latent failure times follow family of Lomax distributions. We obtain various inferences for model parameters when causes of failure are partially known and lifetime data are observed using a generalized progressive hybrid censoring scheme. The existence and uniqueness properties of maximum likelihood estimators of unknown parameters are established. Bayes estimators and associated credible intervals are also obtained. In addition, various inferences for unknown parameters are derived under order-restricted shape parameters of Lomax distributions. Finally, a simulation study is conducted to evaluate the performance of the proposed estimates. A real data set is also analysed for illustration purposes.