THE SIGNAL DETECTION THEORY ROC CURVE: SOME APPLICATIONS IN FOOD SENSORY SCIENCE
Article first published online: 1 APR 2008
© 2008, The Author(s)
Journal of Sensory Studies
Volume 23, Issue 2, pages 186–204, April 2008
How to Cite
O'MAHONY, M. and HAUTUS, M.J. (2008), THE SIGNAL DETECTION THEORY ROC CURVE: SOME APPLICATIONS IN FOOD SENSORY SCIENCE. Journal of Sensory Studies, 23: 186–204. doi: 10.1111/j.1745-459X.2007.00149.x
- Issue published online: 1 APR 2008
- Article first published online: 1 APR 2008
- Accepted for Publication April 20, 2007
In psychology, the receiver operating characteristic (ROC) curve is a key part of Signal Detection Theory, which is used for calculating d′ values in discrimination tests. In food sensory science, the ROC curve can also be a useful tool. To give a specific example, it is not always convenient to use forced-choice protocols for difference tests; foods may be fatiguing, and assessments with single presentations, like the Yes–No procedure, might be more appropriate. In this case, ROC curves provide a useful method for computing d′ values. More generally, ROC curves give information about cognitive strategies. Cognitive strategies are important for difference tests. Values of d′ can only be computed if the cognitive strategy used in the test is known.
When using methods other than two-alternative forced-choice in difference testing, a receiver operating characteristic (ROC) curve would be required to compute d′. This is because when assessing discrimination ability, the cognitive strategy of the subject must be taken into account, and ROC curves can sometimes reveal the cognitive strategy used by the subject. This article describes how the cognitive strategy can be determined from the subject's ROC curve. The hidden assumptions made when using ROC curves and how these assumptions can be tested are also given. This information is essential to researchers in sensory evaluation as well as those using these methods in a practical setting.