Epidemiology

Question 1

Definition of a confounder

Answer 1

A variable that modifies an association between a measured exposure and outcome because it is:

• Associated with the exposure
• A risk factor for the outcome
• Not part of the causal pathway between the exposure and the disease

Question 2

Methods for controlling for confounding

Answer 2

Study design:

• randomisation
• matching
• restriction
• cross-over design

Study analysis:

• stratification
• multivariate analysis (cox proportional hazards, logistic regression, propensity scores).

Question 3

Sources of bias in a case control study

Answer 3

Selection bias:

• control selection bias (control group is not truly representative of the population that produced the cases)
• self-selection bias can occur in case-control studies with low response or participation rates or in studies where cases are drawn from hospitalized cases as these may be very different to non-hospitalized cases
• survivor bias: only cases who are living are selected.

Information/measurement bias

• recall bias (cases may be more likely to recall exposure): can address by verifying exposure from existing records, objective methods of measuring exposure.
• observer bias can occur if interviewers are aware of the case/control status.

Question 4

Odds ratio

Answer 4

An odds ratio is a measure of association between an exposure and an outcome. The OR represents the odds that an outcome will occur given a particular exposure, compared to the odds of the outcome occurring in the absence of that exposure.
OR = ad/bc

Used in case control studies because absolute risks, and therefore relative risks, cannot be estimated.