Mathematically/Statistically Based Validation System

Case Study

car design


Automotive manufacturer General Motors needed an unbiased third party to help them evaluate their computer models and to implement a strategy on test bed problems. Using a good model can help save the company time and money by designing an energy efficient car that performs well in safety testing and is sleek and attractive to the consumer.

Outcomes & Results

GM hired NISS to help test the computer models and to evaluate the confidence limits to the predictions of computer models. They also looked at what the uncertainty estimates would be for predictions that were "beyond the data."

Research Project

NISS defined and developed a strategy for the evaluation of GM computer models, in cooperation with GM scientists, and implemented the strategy on test bed problems. Central research issues included the association of confidence limits to predictions of computer models; uncertainty estimates for predictions "beyond the data;" either in the sense of predicting over a new range of inputs or predicting with a variant of already studied models; and determination of sensitivities in model components.

Research Team: 

Principal Investigator(s): Jerome Sacks, NISS; James Berger, Duke

Individual Team Members: 
Jerome Sacks

Funding Sponsors: