1.sensitivity, also known as recall,true positive rate, means that the predicted positive case is proportional to (true positive) and all facts are positive.
2.specificity, also called, true negative rate, meaning is the proportion of case that is predicted to be negative (true negative) and all facts are negative.
3.roc (receiver operating characteristic)
ROC can be used to evaluate the classification algorithms of two classifications.
The longitudinal axis of the ROC curve is the ratio of sensitivity, which is predicted to be positive in case (true positive) and all facts are positive, and the horizontal axis is fall-out, meaning that it is predicted to be positive and all facts are negative.
The general curve is, by adjusting the threshold, to get different values of true positive rate and false positive rate.
With the ROC curve, the area below the ROC curve can be used to measure the quality of the algorithm.
- .90-1 = Excellent (A)
- .80-.90 = Good (B)
- .70-.80 = Fair (C)
- .60-.70 = Poor (D)
- .50-.60 = Fail (F)
Reference Links:
Http://gim.unmc.edu/dxtests/roc3.htm
Http://en.wikipedia.org/wiki/Sensitivity_and_specificity
Evaluation method of Logistic regression