Goodness of Fit Testing for the Log-Logistic distribution Based on Type I Censored Data

Abstract

The main aim of this thesis is to investigate the problem of the goodness of fit test for Log-Logistic distribution based on empirical distribution function under Type I censored data. The maximum likelihood estimation method is used to estimate the unknown parameters of Log-Logistic distribution. A Monte Carol power studies are conducted to evaluate and compare the performance of the proposed method which is an extension to the test procedure by Pakyari and Balakrishnan (2017) with the existing classical method for several alternative distributions. The proposed method exhibits higher power compared to classical method. Additionally, applications on Type I censored real datasets for the proposed and classical methods are considered for illustrative purposes. As result from the real data it was found that the Log-Logistic model has good fit for the data