TOPICS
Search

Receiver Operating Characteristic Curve


A receiver operating characteristic curve, or ROC curve, plots the sensitivity of a binary diagnostic test or classifier against its false-positive rate as the decision threshold varies. If s is the specificity, then the false-positive rate is 1-s. Thus the horizontal and vertical coordinates of a point on the curve are respectively 1-s and sensitivity.

An ideal test reaches the upper left corner (0,1). A test with equal true- and false-positive rates lies on the diagonal. Youden's J statistic is the greatest vertical distance between the curve and this diagonal.


See also

Sensitivity, Specificity, Youden's J Statistic

Explore with Wolfram|Alpha

References

Fawcett, T. "An Introduction to ROC Analysis." Pattern Recogn. Lett. 27, 861-874, 2006. https://doi.org/10.1016/j.patrec.2005.10.010.

Cite this as:

Weisstein, Eric W. "Receiver Operating Characteristic Curve." From MathWorld--A Wolfram Resource. https://mathworld.wolfram.com/ReceiverOperatingCharacteristicCurve.html

Subject classifications