LINEAR AND BAYESIAN ESTIMATION OF THE PARAMETERS OF THE TYPE II GENERALIZED LOGISTIC DISTRIBUTION BASED ON PROGRESSIVELY TYPE II CENSORED DATA

Abstract

Generalized distributions have become widely used in applications recently. They are very flexible in data analysis, especially with skewed models that are important and occur frequently in many applications. In particular, the Generalized Logistic Distribution with its several types has lately gained a lot of attention in the literature. In this study, based on progressively Type II censored data, we obtained estimators of the unknown parameters of Type II Generalized Logistic Distribution. Several point estimation methods are used. Specifically, we consider the maximum likelihood estimation (MLE), the Bayesian estimator based on importance sampling and Lindley's approximation, the linear estimators (BLUE and BLEE). The estimators were investigated and compared using simulation techniques in a variety of scenarios and progressive censoring schemes. The criteria used for comparison are the mean squared error (MSE) and bias. The derived estimators are applied to real-world data in order to see how they operate in real situations.