Document Details

Document Type : Thesis 
Document Title :
BIVARIATE GENERALIZED EXPONENTIAL DISTRIBUTION BASED ON FARLIE GUMBEL- MORGENSTERN (FGM) COPULAS
التوزيع الاسي المعمم الثنائي على اساس رابطة فارلي- غامبل- مور غنسترن
 
Subject : Faculty of Sciences 
Document Language : Arabic 
Abstract : The generalized exponential distribution is an important distribution for studying lifetime data. It is considered as a suitable alternative to the most common lifetime distributions such as gamma and Weibull distributions. In recent studies, bivariate and multivariate extensions of generalized exponential distribution are constructed and studied in different ways. Copula is one of the commonly approaches to construct bivariate and multivariate dependent distributions. This thesis aims to form and study the bivariate extension of the generalized exponential distribution based on copula. In this thesis, three copulas are used to construct three models of bivariate generalized exponential distribution which are Farlie-Gumbel-Morgenstern, Plackett and Gaussian copulas. Different estimation methods are applied for estimating the unknown parameters of the proposed bivariate models. A simulation study is performed to evaluate the performance of these estimation methods. The estimates of parameters are compared by the relative mean square errors of estimates at different values of parameters and different sample sizes. The simulation study showed that the maximum likelihood estimation provides efficient estimates for parameters in most of cases compared to other estimation methods. Finally, a real data set is analyzed and showed that the bivariate generalized exponential distribution based on Plackett copula provides a better fit compared to the other proposed bivariate generalized exponential distributions. 
Supervisor : Dr. Lutfiah Ismail Al turk 
Thesis Type : Master Thesis 
Publishing Year : 1439 AH
2017 AD 
Co-Supervisor : Dr. Mervat Khalifa Abd Elaal 
Added Date : Tuesday, December 12, 2017 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
رحاب سالم جروانGarwan, Rehab SalemResearcherMaster 

Files

File NameTypeDescription
 42946.pdf pdf 

Back To Researches Page