الفهرس 
PrefaceOnly 14 pages are availabe for public view
 |  | from | 149 |  |  |
| | | from | 149 | | |
Abstract
Accelerated life tests (ALTs) are preferred to be used in manufacturing
industries to obtain the required information about the reliability of product components and materials in a short period of time. Data collected at such accelerated conditions are extrapolated through a physically suitable statistical model to estimate the lifetime distribution at design condition stress. The stress can be applied in different ways: commonly used methods : are constant stress, progressive stress and step stress (see Nelson 1999).
The two-parameter generalized exponential distribution has become one of most important distributions both on theoretical and practical grounds, especially, in the engineering, the physical and the electrical studies. It was _rst introduced by Gupta and Kundu (1999).
Statistical estimation is to obtain some estimates (either point or interval) for the unknown population parameters based on some given data from the same population. On the other hand, statistical prediction is to obtain some estimates (either point or interval) for future ”unobserved” data, rather than the population parameters, based on past (informative) data from the same population. These available data could be obtained in
many different types. One general and important type of data is progressive censoring. The main purpose of the Thesis is to obtain statistical estimation and prediction for the generalized exponential distribution under accelerated condition based on progressive type-II censoring. The Thesis contains four chapters.
Chapter 1: contains some basic concepts which will be used through this thesis. Also, it contains a historical survey on some studies in theoretical and application which have been made on the generalized exponential distribution since its formulation until the latest issued researches. Finally it contains a description of the under-study problem.
Chapter 2: is devoted to find maximum likelihood and Bayes estimation for the two parameters α and λ of the the generalized exponential distribution and the acceleration parameter γ based on constant partially accelerated life tests. Two cases are considered. In the first case, the parameter λ is assumed to be known while in the second case, the three parameters α , λ and γ are assumed to be unknown. Numerical examples for the given procedures and Monte Carlo simulation study is used to
compare the different estimates.
Chapter 3: is devoted to find maximum likelihood and Bayes estimation for the parameter α of the generalized exponential distribution and the acceleration parameter β based on step-stress partially accelerated life tests. One case is considered. In this case, the parameter λ is assumed to be known. Numerical examples for the given procedures and Monte Carlo
simulation study is used to compare the different estimates.
Chapter 4: Bayesian prediction bounds are obtained for future constant accelerated life tests under the generalized exponential distribution based on two-sample technique. The two and three parameters cases are considered. Finally, numerical illustration for the given procedure and a simulation study are given.