Inference of dependent left-truncated and right-censored competing risks data from a general bivariate class of inverse exponentiated distributions. Issue 2 (4th March 2022)

• Record Type: Journal Article
• Authors: Wang, Liang; Lio, Yuhlong; Tripathi, Yogesh Mani; Dey, Sanku; Zhang, Fode
• Is Part Of: Statistics. Volume 56:Issue 2(2022)
• Page Start: 347
• Page End: 374
• Publication Date: 2022-03-04
• Subjects: Dependence competing risks model -- left-truncated and right-censored data -- a general class of inverse exponentiated distributions -- maximum likelihood estimation -- posterior analysis; Mathematical statistics -- Periodicals; 519.505
• DOI: 10.1080/02331888.2022.2047680
• Languages: English
• ISSNs: 0233-1888

Abstract

Abstract : In this paper, inference is discussed for left-truncated and right-censored (LTRC) competing risks data. For modelling the dependent competing risks variables, a flexible bivariate lifetime model is constructed with a class of inverse exponentiated distribution, and associated distribution properties are provided correspondingly. When the LTRC competing risks data is available with partially observed failure causes, a dependent competing risks model is further established. Maximum likelihood estimators of the unknown parameters and the reliability indices are established, and the approximate confidence intervals are also constructed based on asymptotic theory. In addition, Bayesian estimators are obtained based on flexible priors, Markov Chain Monte Carlo sampling approach is also proposed for computing the Bayesian estimates as well as the highest posterior density credible intervals. Finally, simulation studies are carried out to investigate the performances of our results, and a real-life data set is analysed to illustrate the applicability of the proposed methods.