Chapter 15- Confounding

Question 1

Confounding

Answer 1

In a study determining whether exposure A is a cause of disease B, we say that the third factor, factor X, is a confounder if:
1. Factor X is a known risk factor for disease B
2. Factor X is associated with exposure A, but is not a result of exposure A
3. Not be an intermediate “cause” between the exposure & outcome

Question 2

How does confounding cause a issue in making a causal claim?

Answer 2

An association may be observed only due to confounding. We need to ask whether an association is actually causal or whether it’s a result of confounding by a third factor that is both a risk factor for the disease and is associated with the disease in question

Question 3

2 approaches to address confounding with statistical analysis

Answer 3

1. Stratification
2. Statistical adjustment

Question 4

2 approaches to address confounding with study design

Answer 4

1. Restriction of eligibility criteria of study population
2. Matching cases/controls –or– exposed/unexposed on confounding factor

Question 5

Bias

Answer 5

Any systematic error in the design, conduct, or analysis of a study that results in the
mistaken estimate of an exposure’s effect on the risk of disease. Inaccurate representation of risk (or odds) comparison

Question 6

3 sources of bias in epidemiological studies

Answer 6

1. Confounding
2. Selection Bias
3. Information Bias

Question 7

Selection Bias

Answer 7

Systematic bias due to sampling or retention. Oversampling of exposed OR unexposed is not enough to produce bias

Question 8

Non-differential Information Bias

Answer 8

What if measurement incorrect for all? Most cases will underestimate effect

Question 9

Biological interaction

Answer 9

When the risk of disease in the presence of two or more risk factors differs from
the risk expected from their individual effects