Statistical model selection for better prediction and discovering science mechanisms that affect reliability
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Statistical Sciences Group
- ARDEC, Picatinny Arsenal, Township, NJ (United States)
Understanding the impact of production, environmental exposure and age characteristics on the reliability of a population is frequently based on underlying science and empirical assessment. When there is incomplete science to prescribe which inputs should be included in a model of reliability to predict future trends, statistical model/variable selection techniques can be leveraged on a stockpile or population of units to improve reliability predictions as well as suggest new mechanisms affecting reliability to explore. We describe a five-step process for exploring relationships between available summaries of age, usage and environmental exposure and reliability. The process involves first identifying potential candidate inputs, then second organizing data for the analysis. Third, a variety of models with different combinations of the inputs are estimated, and fourth, flexible metrics are used to compare them. As a result, plots of the predicted relationships are examined to distill leading model contenders into a prioritized list for subject matter experts to understand and compare. The complexity of the model, quality of prediction and cost of future data collection are all factors to be considered by the subject matter experts when selecting a final model.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- AC52-06NA25396
- OSTI ID:
- 1224056
- Report Number(s):
- LA-UR-15-21723; PII: systems3030109
- Journal Information:
- Systems, Vol. 3, Issue 3; ISSN 2079-8954
- Publisher:
- MDPICopyright Statement
- Country of Publication:
- United States
- Language:
- English
Comparing the Reliability of Related Populations With the Probability of Agreement
|
journal | July 2016 |
Comparing the Reliability of Related Populations With the Probability of Agreement
|
dataset | April 2017 |
Comparing the Reliability of Related Populations With the Probability of Agreement [Supplemental Data]
|
dataset | April 2017 |
Similar Records
Diversity and the citizens' advisory board: aligning disparate views for better results - 15469
Center for Theoretical Underground Physics and Related Areas - CETUP*2013 Summer Program