|
Activity Number:
|
226
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Defense and National Security
|
| Abstract - #305633 |
|
Title:
|
Planning Surveillance for a Stockpile That Might Degrade
|
|
Author(s):
|
Scott Vander Wiel*+ and C. Shane Reese and Alyson Wilson and Todd Graves
|
|
Companies:
|
Los Alamos National Laboratory and Brigham Young University and Iowa State University and Los Alamos National Laboratory
|
|
Address:
|
MS F600, Los Alamos, NM, 87545,
|
|
Keywords:
|
|
|
Abstract:
|
Weapons stockpiles are expected to have high reliability over time. Prudence demands regular testing of sampled units to demonstrate that aging effects have not affected reliability. Managers need to know how reliability estimates will be affected if surveillance sampling is curtailed or ramped down to lower levels to save money. The question is not easily answered because reliability estimation is a diverse process carried out across multiple organizations. This poster describes a model for a stockpile expected to have high reliability from one year to the next, but with an ever-present possibility that reliability could begin to decline at any time. The model provides a framework for answering questions about the effect of reduced sampling on reliability estimates and confidence bounds.
|
