Question: The below data set considers whether a disease would be present (Y = Yes, disease present, N = No disease present) based on the concentration
The below data set considers whether a disease would be present (Y = Yes, disease present, N = No disease present) based on the concentration of a biochemical indicator in the blood.
What would you expect the area under the ROC curve to be for this data set if with a predictive function of x > .5 = Y ? Explain if this is a good score.
| Concentration (x) | Disease Present | Y Sum | N Sum | Sensitivity | False Positive Rate |
0.95 | Y | 1 | 0 | 0.2 | 0 |
0.89 | Y | 2 | 0 | 0.4 | 0 |
0.86 | Y | 3 | 0 | 0.6 | 0 |
0.77 | Y | 4 | 0 | 0.8 | 0 |
0.74 | Y | 5 | 0 | 1 | 0 |
0.4 | N | 5 | 1 | 1 | 0.2 |
0.38 | N | 5 | 2 | 1 | 0.4 |
0.37 | N | 5 | 3 | 1 | 0.6 |
0.36 | N | 5 | 4 | 1 | 0.8 |
0.33 | N | 5 | 5 | 1 | 1 |
Please send me answer in type form strictly prohibited handwritten solution.
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
