Three hundred cases and 600 controls were selected among mothers for a case-control study to see if maternal coffee consumption was related to low birth weight in the mothers’ babies.

Q1:

Three hundred cases and 600 controls were selected among mothers for a case-control study to see if maternal coffee consumption was related to low birth weight in the mothers’ babies. Data were collected on past coffee consumption patterns for the mothers and on cigarette smoking, a known risk factor for low birth weight. Coffee consumption was also positively correlated with smoking.

If we do not adjust for smoking, our estimate of the relative risk of low birth weight associated with coffee consumption is… 

Choose one answer:

An overestimate of the true association

An underestimate of the true association

The same as the true association

Q2:

A variable must cause both exposure and disease in order to be considered a confounder of the association.

Choose one answer:

True

False

Q3:

Which one of the following approaches to control of confounding is most likely to affect the external validity (i.e. generalizability) of a study?

Choose one answer:

Randomization

Regression analysis

Stratified analysis

Restriction

Q4:

In a study evaluating the association between physical inactivity and heart disease, age is found to be positively associated with both. The primary mechanism by which physical inactivity is thought to cause heart disease is via hemodynamic effects.

Match each variable with its correct role:

Heart disease:   a. Outcome   b. Confounder   c. Mediator    d. Exposure 

Physical inactivity:  a. Outcome   b. Confounder   c. Mediator    d. Exposure

Changes in hemodynamics:   a. Outcome   b. Confounder   c. Mediator    d. Exposure

Age:  a. Outcome   b. Confounder   c. Mediator    d. Exposure

Q5:

Same scenario: in a study evaluating the association between physical inactivity and heart disease, age is found to be positively associated with both. The primary mechanism by which physical inactivity is thought to cause heart disease is via hemodynamic effects.

If we want to estimate the true association between physical inactivity and heart disease, we need to adjust for (check all that apply):

Hemodynamic effects

Age

Both age & hemodynamic effects

Nothing