@Hichem: thanks for the explanation. But I have problem in plotting them. I have developed a machine learning method to classify query data into any one of the four classes. And after conducting Jackknife test i calculated the TP TN FP FN and with that sensitivity and specificity. Now i have sensitivity and specificity for for each class like 0.94;0.75;0.91;0.76; and 0.92;0.99;0.96; 0.96; respectively. Can ROC curve can be drawn for this ?? the values are sensitivity and specificity of FOUR different classes!! kindly guide me in this regard.
This paper introduces a detailed explanation with numerical examples many classification assessment methods or classification measures such as:
Accuracy, sensitivity, specificity, ROC curve, Precision-Recall curve, AUC score and many other metrics. In this paper, many details about the ROC curve, PR curve, and Detection Error Trade-off (DET) curve. Moreover, many details about some measures which are suitable for imbalanced data are explained.