a person has a particular disease. Suppose that 95% of the people tested
do not suffer from the disease. (That is,
pos
corresponds to 5% and
neg
to 95% of the test cases.) Consider the following classi±ers:
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentPractice Exercises
3
•
Classifer
C
1
which always predicts negative (a rather useless clas
sifer oF course).
•
Classifer
C
2
which predicts positive in 80% oF the cases where the
person actually has the disease, but also predicts positive in 5% oF
the cases where the person does not have the disease.
•
Classifer
C
3
which predicts positive in 95% oF the cases where the
person actually has the disease, but also predicts positive in 20%
oF the cases where the person does not have the disease.
Given the above classifers, answer the Following questions.
a.
±or each oF the above classifers, compute the accuracy, precision,
recall and specifcity.
b.
IF you intend to use the results oF classifcation to perForm Further
screening For the disease, how would you choose between the
classifers.
c.
On the other hand, iF you intend to use the result oF classifcation
to start medication, where the medication could have harmFul
eFFects iF given to someone who does not have the disease, how
would you choose between the classifers?
Answer:
No Answer
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '13
 Dr.Khansari
 Data Mining, sourcedriven architecture

Click to edit the document details