Observational studies

Question 1

Why would you choose an observational study design over e.g. an RCT?

Answer 1

• Less practical issues
• True internal en external validity
• Less ethical problem (since no intervention)

Question 2

What is the defintion of:
- internal validity
- external validity

Answer 2

• internal validity → the degree of confidence that the causal relationship you are testing is not influenced by other factors or variables
• external validity → the extent to which results of a study can be generalized to other contexts.

Question 3

Objectives of studies can be: incidence, prevalence, cause, prognosis and treatment effect.
- Describe what study objective fits with each study design (cohort, cross-sectional, case-control, RCT).

Answer 3

• Cohort → incidence, cause, prognosis
• Cross-sectional → prevalence, cause
• Case-control → cause
• RCT → treatment effect

Question 4

What kind of factor is time in regard to observational study designs?

Answer 4

• During observational studies, the exposure has already happened.
• Causal inference is based on temporality
• There is only a time line of registration of observations.

Question 5

What is the difference between census and samping and what does this have to do with observational study designs?

Answer 5

• Census → gathering information about every member of the population (population based research)
• Sampling → gathering information only about a part (i.e. sample), to represent the whole.

The problem with observational design is sampling and more specifically sampling bias → members of a certain population that are more likely to be chosen in a sample than others.

Question 6

A type of sampling bias is the survivor bias. What does this bias mean?

Answer 6

It is the tendency to concentrate on people or things that made it past some selection process and overlooking those that did not (e.g. looking at the treatment effect while focusing on the ones that have survived the first week after treatment, but overlooking those who died after the first week).

Question 7

What are advantages and disadvantages of cohort studies?

Answer 7

• Advantages → ethical (compared to RCT) and multiple outcome variables.
• Disadvantages → subject selection and confounding variables

Question 8

What are advantages and disadvantages of a cross-sectional study?

Answer 8

• Advantages → prevalence, quick/cheap
• Disadvantages → causation is not the same as association, inaccurate for rare conditions

Question 9

What are advantages of disadvantages of case-control studies?

Answer 9

• Advantages → few subjects required, long period between exposure and disease
• Disadvantages → confounding variables, sampling bias