Inferences on Unified Progressive Hybrid Censoring utilizing Weibull-Half-Logistic Distribution with Application to Micro Drop Data

Abstract

In this paper, we have delved into the application of classical and Bayesian approaches for the Weibull-half-logistic distribution based on unified progressive hybrid censoring scheme. Maximum likelihood estimation is employed for the two parameters, and the establishment of approximate confidence bounds is based on asymptotic normality. The Lindley’s approximation and Markov chain Monte Carlo technique from the squared error and Linex loss functions are performed to obtain the symmetric and asymmetric Bayesian inferences. The credible bounds of the unknown parameters are also provided. The performance of the suggested technique and estimators has been assessed and compared using the outcomes of simulated data with the censoring strategies utilized. Finally, for illustrative purposes, the virus-containing micro drop data under simultaneous airflow with velocity of 0.2^m/s is examined.