Skip to main content
Mail a PDF copy of this page to:
(Your email address will not be added to a mailing list)
Show menu

Comparison of ROC curves

Next selectROC curves
Next selectComparison of ROC curves


Use Comparison of ROC curves to test the statistical significance of the difference between the areas under 2 to 6 dependent ROC curves (derived from the same cases) with the method of DeLong et al. (1988) or Hanley & McNeil, 1983.

Required input

In the dialog box you need to enter:

Dialog box for comparison of ROC curves




When you have completed the dialog box, click OK to proceed.


The results window shows the data for the different ROC curves followed by the result of pairwise comparison of all ROC curves: the difference between the areas, the standard error, the 95% confidence interval for the difference and P-value. If P is less than the conventional 5% (P<0.05), the conclusion is that the two compared areas are significantly different.

Comparison of ROC curves - statistics

Display Roc curves

When you have selected Display ROC curves window in the dialog box, the program will also open a graph window with the different ROC curves.

Comparison of ROC curves - graph


See also

Recommended book

Book cover

The Statistical Evaluation of Medical Tests for Classification and Prediction
Margaret Sullivan Pepe

Buy from Amazon

This book describes statistical concepts and techniques for evaluating medical diagnostic tests and biomarkers for detecting disease. More generally, the techniques pertain to the statistical classification problem for predicting a dichotomous outcome. Measures for quantifying test accuracy are described including sensitivity, specificity, predictive values, diagnostic likelihood ratios and the Receiver Operating Characteristic Curve that is commonly used for continuous and ordinal valued tests.