Sensitivity Testing: Theory and Practice

• Activity Number: 195
• Type: Roundtables
• Date/Time: Monday, August 4, 2014 : 12:30 PM to 1:50 PM
• Sponsor: Quality and Productivity Section
• Author(s): Barry Neyer*+
• Companies: Excelitas Technologies
• Keywords: Sensitivity Testing ; efficient design ; extreme level ; applied

Abstract

Sensitivity tests often are used to estimate the parameters associated with latent continuous variables that cannot be measured. For example, in testing the sensitivity of an airbag initiator to electrical current, each specimen is assumed to have a critical electrical current level or threshold. Currents larger than this level will always initiate the initiator and deploy the airbag, but smaller currents will not. Repeated testing of any one sample is not possible, because the current that is not sufficient to cause initiation nevertheless will generally damage the specimen. To characterize the probability of response, samples are tested at various current levels, the response or lack thereof is noted, and the data are analyzed to provide estimates of population parameters. This roundtable will present several examples illustrating the general approach, as well as some of the potential pitfalls present when interpreting the analysis. Participants are encouraged to bring test cases or questions they wish to discuss.