Lecture 9 9/12/24

Question 1

What is an ROC curve?

Answer 1

a plot of sensitivity on the y axis against (1-specificity) on the x axis for varying values of the threshold/cut off point

Question 2

What is the use of the ROC curve?

Answer 2

to identify a sensitivity/specificity combination that maximizes both values

Question 3

What is the result of a low cut off for positive results?

Answer 3

-high sensitivity
-low specificity

Question 4

What is the result of a high cut off for positive results?

Answer 4

-low sensitivity
-high specificity

Question 5

How does a low cut off for positive tests affect false positive and false negative results?

Answer 5

-more false positive results
-less false negative results

Question 6

How does a high cut off for positive tests affect false positive and false negative results?

Answer 6

-more false negative results
-less false positive results

Question 7

How do the PPV and NPV relate to sensitivity and specificity?

Answer 7

-PPV lowers when sensitivity is higher and specificity is lower
-NPV lowers when specificity is higher and sensitivity is lower

Question 8

How does prevalence impact PPV and NPV values?

Answer 8

increased prevalence increased PPV and decreases NPV