Which measure is most important for evaluating the performance of clas

QUESTION

Which measure is most important for evaluating the performance of classifiers, models that predict class membership?

a. Root mean squared error (RMSE)
b. Area under the receiver operating characteristic (ROC) curve
c. Percentage of correctly classified cases
d. Hosmer-Lemeshow statistic

ANSWER:

ANS: B
The area under the receiver operating characteristic (ROC) curve is the most important overall measure of classifier performance.