Statistical model selection for better prediction and discovering science mechanisms that affect reliability
Abstract
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.
- Authors:
-
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Statistical Sciences Group
- ARDEC, Picatinny Arsenal, Township, NJ (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1224056
- Report Number(s):
- LA-UR-15-21723
Journal ID: ISSN 2079-8954; PII: systems3030109
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Systems
- Additional Journal Information:
- Journal Volume: 3; Journal Issue: 3; Journal ID: ISSN 2079-8954
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; automated model evaluation; variable selection, environmental exposure, system usage, advancing underlying theory
Citation Formats
Anderson-Cook, Christine M., Morzinski, Jerome, and Blecker, Kenneth D. Statistical model selection for better prediction and discovering science mechanisms that affect reliability. United States: N. p., 2015.
Web. doi:10.3390/systems3030109.
Anderson-Cook, Christine M., Morzinski, Jerome, & Blecker, Kenneth D. Statistical model selection for better prediction and discovering science mechanisms that affect reliability. United States. https://doi.org/10.3390/systems3030109
Anderson-Cook, Christine M., Morzinski, Jerome, and Blecker, Kenneth D. Wed .
"Statistical model selection for better prediction and discovering science mechanisms that affect reliability". United States. https://doi.org/10.3390/systems3030109. https://www.osti.gov/servlets/purl/1224056.
@article{osti_1224056,
title = {Statistical model selection for better prediction and discovering science mechanisms that affect reliability},
author = {Anderson-Cook, Christine M. and Morzinski, Jerome and Blecker, Kenneth D.},
abstractNote = {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.},
doi = {10.3390/systems3030109},
journal = {Systems},
number = 3,
volume = 3,
place = {United States},
year = {Wed Aug 19 00:00:00 EDT 2015},
month = {Wed Aug 19 00:00:00 EDT 2015}
}
Figures / Tables:
Works referenced in this record:
System Health Assessment
journal, March 2011
- Collins, David H.; Anderson-Cook, Christine M.; Huzurbazar, Aparna V.
- Quality Engineering, Vol. 23, Issue 2
A new look at the statistical model identification
journal, December 1974
- Akaike, H.
- IEEE Transactions on Automatic Control, Vol. 19, Issue 6
Estimating the Dimension of a Model
journal, March 1978
- Schwarz, Gideon
- The Annals of Statistics, Vol. 6, Issue 2
Bayesian measures of model complexity and fit
journal, October 2002
- Spiegelhalter, David J.; Best, Nicola G.; Carlin, Bradley P.
- Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 64, Issue 4
Optimal predictive model selection
journal, June 2004
- Barbieri, Maria Maddalena; Berger, James O.
- The Annals of Statistics, Vol. 32, Issue 3
Model Selection for Good Estimation and Prediction over a User-Specified Covariate Distribution for Linear Models under the Frequentist Paradigm
journal, October 2011
- Pintar, Adam; Anderson-Cook, Christine M.; Wu, Huaiqing
- Quality and Reliability Engineering International, Vol. 28, Issue 7
Optimization of Designed Experiments Based on Multiple Criteria Utilizing a Pareto Frontier
journal, November 2011
- Lu, Lu; Anderson-Cook, Christine M.; Robinson, Timothy J.
- Technometrics, Vol. 53, Issue 4
Incorporating response variability and estimation uncertainty into Pareto front optimization
journal, October 2014
- Chapman, Jessica L.; Lu, Lu; Anderson-Cook, Christine M.
- Computers & Industrial Engineering, Vol. 76
Least angle regression
journal, April 2004
- Tibshirani, Robert; Johnstone, Iain; Hastie, Trevor
- The Annals of Statistics, Vol. 32, Issue 2
QQ Models: Joint Modeling for Quantitative and Qualitative Quality Responses in Manufacturing Systems
journal, April 2015
- Deng, Xinwei; Jin, Ran
- Technometrics, Vol. 57, Issue 3
Optimal predictive model selection
text, January 2004
- Barbieri, Maria Maddalena; Berger, James O.
- arXiv
Works referencing / citing this record:
Comparing the Reliability of Related Populations With the Probability of Agreement
journal, July 2016
- Stevens, Nathaniel T.; Anderson-Cook, Christine M.
- Technometrics, Vol. 59, Issue 3
Comparing the Reliability of Related Populations With the Probability of Agreement
dataset, April 2017
- Stevens, Nathaniel T.; Anderson-Cook, Christine M.
- Figshare, 1.08 MB
Comparing the Reliability of Related Populations With the Probability of Agreement [Supplemental Data]
dataset, April 2017
- Stevens, Nathaniel; Anderson-Cook, Christine
- figshare-Supplementary information for journal article at DOI: 10.1080/00401706.2016.1214180, 1 PDF file (1.08 MB)
Figures / Tables found in this record: