Title of the talk: Analysis for Left-Truncated and Right-Censored Competing Risks Data from Marshall-Olkin Bivariate Generalized Lifetime Family

Date, Time & Venue: 18 May 2026 at 11:00 A.M on Seminar room, Dept. of Mathematics

Abstract: This talk discusses statistical inference for a left-truncated and right-censored competing risks model when the causes of failure are partially observed and dependent. The latent failure times are assumed to follow the Marshall–Olkin Bivariate Generalized Lifetime Distribution framework. Both frequentist and Bayesian approaches are developed for estimating the unknown model parameters. Maximum likelihood estimators, along with their existence and uniqueness properties, are obtained, and approximate confidence intervals are constructed using the observed Fisher information matrix. Bayesian inference is carried out using a Gamma–Dirichlet prior under squared error, and LINEX loss functions, and inference under order restrictions on parameters is also considered. The performance of the proposed methods is assessed through extensive simulation studies, and the methodology is illustrated using two real-life datasets.

About the Speaker: Dr. Prakash Chandra is an Assistant Professor in the Department of Mathematics at BIT, Mesra. He earned his Ph.D. in Statistics from the IIT Patna (2024), where his research focused on statistical inference, particularly in competing risk models under censored and truncated data. He holds an M.Sc. in Statistics and Computing from Banaras Hindu University and a B.Sc. (Hons.) in Statistics from Patna University.

Dr. Chandra’s research interests include statistical inference, reliability analysis, optimal life testing plans, and machine learning. Before his current role, he served as an Assistant Professor at SRM University AP and worked as a Statistical Trainee at the Indian Statistical Institute, Kolkata.