A Dynamic Competing Risk Model for Filtering Reliability and Tracking Survivability

The motivation for this dissertation is the resolution of a long-standing practical problem in reliability engineering, namely that of tracking reliability growth. The dissertation's essential output is the development of a coherent framework for casting the reliability growth problem as one of filtering, prediction, and tracking. This constitutes a paradigm shift in how reliability is monitored, namely as a dynamic system. The two by-products of this dissertation are: a probabilistic competing risk model and a reconsideration of the foundations of reliability via Popper's notion of propensity.

Author

• Martin, Owen S.

Language

• en

Keyword

• propensity
• reliability growth
• kalman filter
• bayesian

Date created

• 2012

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Statistics

Degree

• Ph.D.

Advisor

• Singpurwalla, Nozer D

Committee Member(s)

• Bura, Efstathia
• Nayak, Tapan K
• Cohen, Michael
• Bose, Sudip

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/jh343s320