Maximum Likelihood Estimate for a Generalized Gamma Distribution Under Progressive First Failure Censoring

• Activity Number: 660
• Type: Contributed
• Date/Time: Thursday, August 13, 2015 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Computing
• Author(s): Yuhlong Lio* and Yu-Jau Lin and Nan Jiang and Tzong-Ru Tsai
• Companies: University of South Dakota and Chung Yuan Christian University and University of South Dakota and Tamkang University
• Keywords: Maximum Likelihood Estimate ; Progressive first failure censoing

Abstract

Gamma distribution is one of widely used models for lifetime and reliability studies. The Maximum likelihood estimates (MLEs) for the parameters of the generalized Gamma distribution, which has three parameters, have been known to be complicated. In this study, a Cross Entropy (CE) method is developed for the MLEs of generalized Gamma distribution parameters based on Progressive first failure sample. A simulation study is used to investigate the performance of this newly developed computation procedure. Finally an example will be used for illustration.