U.S.-Egypt Cooperative Research: Informational and Statistical Research Topics on Aging
U.S.-Egypt Cooperative Research: Informational and Statistical Research Topics on Aging
Ahmad, Ibrahim
University of Central Florida, Orlando, FL, United States
Fiscal Year 2004
Abstract[عدل]
This award is to support a cooperative research between Dr. Ibrahim Ahmad, Department of Statistics, University of Central Florida, Orlando, Florida and Dr. Hady Ahmed, Department of Mathematical Statistics and Operations Research, Institute of Statistical Studies and Research, Cairo University, Cairo, Egypt. In life testing three notions dominate its development, these are the random life itself, the random residual life at a specific time t and the equilibrium or stationary random life. Based on various types of stochastic comparisons of these random variables, classes of life distributions that characterize decay in life have been introduced and studied in the literature for several decades now. Past-developed notions, such as the Hazard Rate and the Mean Residual Life, have proven useful in many areas including medicine, biostatistics, reliability and quality and insurance. The PIs will study new notions that are important in different studies as Forensic science (time since death), Geriatrics (studying old age), Times since Failure (in production lines). These new notions include the "Reversed hazard rate" and the "Mean inactivity time". From these the PIs will define new classes that address life from new angles. The PIs will apply this approach to the interrelations between basic reliability and life testing functions, all to be defined in terms of stochastic comparison. The research unifies the treatment of ageing families of life distributions, makes it easier to relate a large number of such classes to one another and define containment properties clearly. It also helps in defining physical interpretations of newly formed classes as related to already known ones, and makes it much easier to proceed with the statistical inference of classes of ageing distributions via testing and estimation.
Scope and broad impact: This project will develop probabilistic properties of new notions for life estimation and the classes defined based on them. It will provide characterizations of these classes, formation of shock model classes and their inference (estimation and hypotheses testing). The unifying approach gives practical values (statistical and physical) to some definitions of ageing classes of life distributions, and develops new statistical and probabilistic properties of such classes. This should open the door for research in life testing multivariate distributions via the new technology. The method is hoped to renew research interest in many areas in reliability and life testing. In the inferential parts the project will address cases of different sampling schemes usually usable in the studies of life data such as censoring, truncation, micro-array data, and panel data among others. This project is being supported under the US-Egypt Joint Fund Program, which provides grants to scientists and engineers in both countries to carry out these cooperative activities.
