A Framework for Validation of Computer Models

• Published in: Technometrics Vol. 49; no. 2; pp. 138 - 154
• Main Authors: Bayarri, Maria J, Berger, James O, Paulo, Rui, Sacks, Jerry, Cafeo, John A, Cavendish, James, Lin, Chin-Hsu, Tu, Jian
• Format: Journal Article
• Language: English
• Published: Alexandria, VI Taylor & Francis 01.05.2007; Milwaukee, WI The American Society for Quality and The American Statistical Association; American Society for Quality Control; American Statistical Association; American Society for Quality
• Subjects: Accuracy; Applied sciences; Approximation; Bayesian analysis; Bias; Calibration; Computer analysis; Computer based modeling; Computer modeling; Computer science; control theory; systems; Data models; Data processing. List processing. Character string processing; Exact sciences and technology; Identifiability; Mathematics; Maximum likelihood estimation; Memory organisation. Data processing; Model discrepancy; Modeling; Motivation; Parametric models; Prediction; Probability and statistics; Sciences and techniques of general use; Software; Statistics; Studies; Validity; Welding; Bayes estimation; Multimodel; Information validation; Identifiability; Model discrepancy; Information source; Multiplicity; Prediction; Spot welding; Updating; Modeling; Bayesian analysis
• ISSN: 0040-1706; 1537-2723
• DOI: 10.1198/004017007000000092

We present a framework that enables computer model evaluation oriented toward answering the question: Does the computer model adequately represent reality? The proposed validation framework is a six-step procedure based on Bayesian and likelihood methodology. The Bayesian methodology is particularly well suited to treating the major issues associated with the validation process: quantifying multiple sources of error and uncertainty in computer models, combining multiple sources of information, and updating validation assessments as new information is acquired. Moreover, it allows inferential statements to be made about predictive error associated with model predictions in untested situations. The framework is implemented in a test bed example of resistance spot welding, to provide context for each of the six steps in the proposed validation process.