ePrints

Meta-analysis of exponential lifetime data from Type-I hybrid censored samples

Lookup NU author(s): Dr Kiran Prajapat

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

In this study, in order to do a life testing experiment, sampled units are divided into a prefixed number of groups with equal number of units. Units in all the groups are tested simultaneously and independently and, in each group the experiment is terminated as soon as a prefixed time elapses or a prefixed number of failures occurs. We provide the meta-analysis of an exponential lifetime data from Type-I hybrid censored samples. The main goal of this study is to obtain optimal schemes based on some optimality criteria by minimizing certain cost function that is based on a maximum likelihood estimator of mean lifetime. We provide the maximum likelihood estimator of mean lifetime and its probability density function under this set-up. Various optimal schemes have been provided by minimizing expected total cost incurred during the experiment as the raw moments can be obtained explicitly. Numerical results on bias and mean squared error of the maximum likelihood estimator have been reported. We also provide confidence intervals of the unknown parameter. For illustration, meta-analysis for a real data set of three groups is presented.

Publication metadata

Author(s): Prajapat K, Mondal S, Mitra S, Kundu D

Publication type: Article

Publication status: Published

Journal: Communications in Statistics: Theory and Methods

Year: 2024

Volume: 53

Issue: 11

Pages: 3973-3991

Print publication date: 01/06/2024

Online publication date: 01/02/2023

Acceptance date: 08/01/2023

ISSN (print): 0361-0926

ISSN (electronic): 1532-415X

Publisher: Taylor & Francis

URL: https://doi.org/10.1080/03610926.2023.2169048

DOI: 10.1080/03610926.2023.2169048

Altmetrics

Share