Invited Speaker
Dr. Shikhar Tyagi
Department of Data Science and Statistics, Christ Deemed to be University, Bangalore, IndiaSpeech Title: Weighted Lindley Multiplicative Regression Frailty Models under Random Censored Data
Abstract: The emphasis of conventional survival research methods has historically been on the occurrence of failures over time. The lack of knowledge of related observed and unobserved covariates during the study of such events can have negative consequences. Frailty models are a viable option for investigating the impact of unobserved covariates in this context. In this article, we suppose that frailty multiplies the hazard rate. As a useful method to ensure the effect of unobserved heterogeneity, we propose weighted Lindley (WL) frailty models with generalized Weibull (GW) and generalized log-logistic-II (GLL2) as the baseline distributions. The Bayesian paradigm of Markov Chain Monte Carlo (MCMC) methodology is used to estimate the model parameters. Subsequently, model comparisons are performed via Bayesian comparison techniques. The popular kidney data set is considered to illustrate the results. It is shown that the new models perform better than those based on gamma and inverse Gaussian frailty distributions.