Term: Receiver Operating Characteristic (ROC) Curve
Last Updated: 2007-09-26
The ROC curve is used to evaluate the accuracy of any method of predicting a dichotomous outcome (e.g. Logistic Regression); it graphically represents the trade-off between false positive and false negative rates for every possible cut off. The graph plots the false positive rate on the x-axis and the true positive rate (1 - the false negative rate) on the y-axis. The area under the curve is of primary interest as it measures the correlation between the category predicted by the test and the true category into which the case falls.