Graduation Semester and Year
2017
Language
English
Document Type
Thesis
Degree Name
Master of Science in Mathematics
Department
Mathematics
First Advisor
Suvra Pal
Abstract
In this study, we have considered analysis of lifetime or survival data with right censoring, which is the most common form of censoring encountered in practice. Assuming a fully parametric setup, the main objective is to consider a wider family of distributions for the lifetime and then find the maximum likelihood estimates of the model parameters using some optimization technique available in R statistical software. In this work, the generalized gamma distribution is considered as the distribution for the lifetime which is flexible in the sense that it contains some of the commonly used lifetime distributions, such as Weibull, gamma, and lognormal, as its special case. This flexibility allows us to carry out a formal test of hypothesis to determine a particular distribution within this family that provides an adequate fit to the data. Another objective is to carry out an extensive Monte Carlo simulation study to demonstrate the performance of the estimation method and the flexibility of the generalized gamma family. To demonstrate the flexibility of the generalized gamma family, we carried out a model discrimination using the likelihood ratio test and information-based criteria. Finally, we illustrate the estimation method and the flexibility of the generalized gamma family using a real data.
Keywords
Generalized gamma distribution, Parameter estimation, Model discrimination
Disciplines
Mathematics | Physical Sciences and Mathematics
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Yu, Hongbo, "USE OF GENERALIZED GAMMA DISTRIBUTION IN MODELING" (2017). Mathematics Theses. 25.
https://mavmatrix.uta.edu/math_theses/25
Comments
Degree granted by The University of Texas at Arlington