Next Article in Journal
A Management Framework for Municipal Solid Waste Systems and Its Application to Food Waste Prevention
Previous Article in Journal
Simulation-Based Approach for Studying the Balancing of Local Smart Grids with Electric Vehicle Batteries
Article Menu

Export Article

Open AccessArticle
Systems 2015, 3(3), 109-132; doi:10.3390/systems3030109

Statistical Model Selection for Better Prediction and Discovering Science Mechanisms That Affect Reliability

1
Statistical Sciences Group, Los Alamos National Laboratory, P.O. Box 1663 MS F600, Los Alamos, NM 87545, USA
2
ARDEC, Picatinny Arsenal, Rockaway Township, NJ 07806, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Thomas V. Huynh
Received: 18 March 2015 / Revised: 28 July 2015 / Accepted: 11 August 2015 / Published: 19 August 2015
View Full-Text   |   Download PDF [1066 KB, uploaded 19 August 2015]   |  

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. Finally, 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. View Full-Text
Keywords: automated model evaluation; variable selection; environmental exposure; system usage; advancing underlying theory automated model evaluation; variable selection; environmental exposure; system usage; advancing underlying theory
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Anderson-Cook, C.M.; Morzinski, J.; Blecker, K.D. Statistical Model Selection for Better Prediction and Discovering Science Mechanisms That Affect Reliability. Systems 2015, 3, 109-132.

Show more citation formats Show less citations formats

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Systems EISSN 2079-8954 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top