Stats/Pharm Cram

Question 1

Type 1 error?

Answer 1

Rejecting a null hypothesis that is actually true

Question 2

Type 2 error?

Answer 2

Accepting a null hypothesis that is actually false

Question 3

Best way to analyse data with multiple variables?

Answer 3

Linear regression - if outcome is continuous

Logistic regression - if outcome is binary

Question 4

Sensitivity?

Answer 4

If disease is present how likely they will have a positive test
a / a + c

Question 5

Specificity?

Answer 5

If a disease is not present how likely they are to have a negative test
b / b + d

Question 6

Positive predictive value?

Answer 6

Proportion of people with a positive test who have a disease

a / a + b

Question 7

Negative predictive value?

Answer 7

Proportion of people with a negative test who do not have a disease?
d / c + d

Question 8

Number needed to treat?

Answer 8

1 / absolute risk reduction

Question 9

Best way to reduce type 2 error (accepting a null hypothesis that is actually false)?

Answer 9

Sample size

Question 10

Omission vs commission bias?

Answer 10

Omission bias - inaction is safer than action

Commission bias - action is safer than inaction

Question 11

Measure of association used for survival analysis?

Answer 11

Hazard ratio

Question 12

Cross sectional study design?

Answer 12

Observational

Assess frequency of disease and related RF at a certain time point

Question 13

Cohort study design?

Answer 13

Group with given exposure/RF to group without

See if exposure changes risk of disease

Question 14

Case control study design?

Answer 14

Disease vs no disease (case vs control)

Prior exposure or risk factor

Question 15

Ecological study design?

Answer 15

Observational

Compare different groups or at different time periods