data collection part 2 of 4

Question 1

What is the function of DAG

Answer 1

Summarise the functional, theoretical and speculative

relationships between variables pertinent to our question

Question 2

what covariant must NEVER be adjusted for and why?

Answer 2

Mediator
Part of the causal pathway between the exposure and the outcome and adjusting out could affect a potentially important pathway.

Question 3

what covariant must ALWAYS be adjusted for and why?

Answer 3

Confounder- create a pseudo-causal pathway between the outcome and the exposure which will generate a statistical relationship between the two even when their isn’t one.

Question 4

Which variable might be adjusted for and why?

Answer 4

competing variable- if they cause a substantial amount of variation in the exposure then, adjusting out can make a association between the remainder and the exposure, easier to detect.

Question 5

what are the 4 types of causal relationships.

Answer 5

functional (e.g. no contraception - teenage mother)
empirical (e.g. based on previous statistical analyses)* (this can often be wrong)
theoretical (e.g. teenage grandmother - teenage mother)
speculative (e.g. teenage grandfather - teenage mother)

Question 6

The cause must precede the effect for it to be determined a causal mechanism? true or false

Answer 6

True

Question 7

what does a ‘minimal sufficient adjustment sets’ help do?

Answer 7

reduce the number of covariates you need to collect/measure.