Case-control studies

Question 1

What do you calculate in case-control study in your analysis?

Answer 1

Measure of association ie OR

Question 2

What can you NOT calculate in case-control study in your analysis?

Answer 2

Incidence rate
Incidence risk

We do not usually know the sampling fraction for either cases (SD) or controls (SH), therefore we cannot calculate absolute risks or rates

Question 3

Goal of interpretation of case-control studies, ie what conclusion are you trying to draw from your analysis?

Answer 3

Exposure increases/decreases/keeps same the risk of outcome

Question 4

How do the OR and RR compare in rare diseases?

Answer 4

OR very similar numerically to RR (rare disease assumption)

Question 5

For common diseases, what do measures of OR estimates depend on?

Answer 5

How controls are sampled

Question 6

What is the null hypothesis vs H1 in case-control studies?

Answer 6

Null: OR=1
H1: OR NOT equal to 1

Question 7

What is a key statistical feature of case control studies?

Answer 7

Cases and non-cases have different probabilities of being selected for inclusion i.e. SD ≠ SH

Question 8

What does a OR vs a p value measure?

Answer 8

OR: magnitude of association between risk factor and outcome

p: strength of evidence against null hypothesis

Question 9

Pros and Cons of Case Control Studies

Answer 9

Advantage: Efficient, Quick, Cheap (especially for rare diseases, diseases of long latency)

Disadvantages: - Susceptible to selection bias and recall bias
- Can only estimate relative measures of disease frequency (e.g. odds ratio)

Question 10

Odds ratio for exposure

Answer 10

Odds of exposure in disease/Odds of disease in unexposed

Question 11

Odds of disease

Answer 11

Risk/1-risk

Which in CC studies is worked out as
number of cases/number of persons without disease

Question 12

What are the three ways you can sample controls for case-control studies?

Answer 12

1. Exclusive sampling: from individuals still at risk at end of study period
    odds ratio
2. Inclusive sampling: from individuals at risk at start of the study period
    risk ratio
3. Concurrent sampling: from individuals still at risk when each case occurs
    rate ratio (implies matching on time)
    matched analysis
   (unless time not associated with exposure)