Stats

Question 1

What 2 factors have the greatest impact on the positive predictive value of a test?

Answer 1

Prevalence of the condition being tested for and sensitivity of the test being used

Question 2

How can positive predictive value be calculated?

Answer 2

Number of true positives / no of true positives and true negatives

Question 3

What is the inverse of the number needed to treat known as?

Answer 3

Absolute risk reduction

It is the decrease in risk of a given activity or treatment in relation to the control treatment/activity

Question 4

What is the definition of number needed to treat?

Answer 4

NNT - how many patients would need to receive a treatment to prevent one event

It is the absolute difference between 2 treatments

Question 5

What type of plot is most commonly used to to graphically display meta analyses of RCTs?

Answer 5

Forest plots

Question 6

Compare which values can reflect type 1 and type 2 errors?

Answer 6

Type 1 = P value

Type 2 = Power calculation

Question 7

Compare definitions of type 1 and type 2 errors?

Answer 7

Type 1 errors - a test rejects a null hypothesis which is actually true in the population

Type 2 errors - a test fails to reject a null hypothesis that is actually false in the population