Defense and Security (Susan Paddock, organizer)

C. Shane Reese (Brigham Young University)
A Hierarchical Model for the Reliability of an Anti-aircraft Missle System

Thursday 2:00-2:30, Fountain I

Abstract:

We describe a hierarchical model for assessing the reliability of multi-component systems. Novel features of this model are the natural manner in which failure time data collected at either the component or subcomponent level is aggregated into the posterior distribution, and pooling of failure information between similar components. Prior information is allowed to enter the model in the form of actual point estimates of reliability at nodes, or in the form of prior groupings. Censored data at all levels of the system are incorporated in a natural way through the likelihood specification. The methodology is illustrated with an example from an anti-aircraft missile system.


Thomas J. Sullivan (The Rand Corporation)
Measuring the Effectiveness of Coalition Reconstruction Operations in Iraq

Thursday 2:30-3:00, Fountain I

Abstract:

The speaker was a strategic planner for the Coalition Provisional Authority (CPA) in Baghdad, Iraq from January to June 2004. He was responsible for collecting, analyzing, and presenting data that was used to measure the effectiveness of the massive Coalition stabilization and reconstruction effort in Iraq. In this presentation he will describe; 1) the daily life of a civilian statistician in Iraq, 2) the evolution of the CPA metrics program, 3) the quality and completeness of Iraqi data, 4) the security challenges associated with collecting data in a combat zone, and 5) efforts to build the capacity of Iraqi statistical agencies to produce high-quality time series data.


Alyson Wilson (Statistical Sciences Group, Los Alamos National Laboratory)
Systems Reliability and Experiment Planning

Thursday 3:00-3:30, Fountain I

Abstract:

Assessing systems reliability often requires combining information from many sources with many different characteristics. We consider recent models for combining data that occurs at different levels of the system. Once the reliability model is developed and fit, the next question is often "What tests should I do next?" The answer, of course, depends on what questions need to be answered, what is currently known, what information sources are available, the costs of collecting information, and the overall budget. We provide several examples to illustrate the issues.