lecture 26 - confounding

Question 1

what is confounding

Answer 1

a mixing or muddling of effects when the relationship we are interested in is confused by the effect of something else = the confounder

• risk factors party together

Question 2

what are the three properties of a potential confounder

Answer 2

• independently associated with the outcome
• independently associated with the exposure
• not on the causal pathway

Question 3

what does independently associated with the outcome mean

Answer 3

• a risk factor for the outcome itself

Question 4

what does independently associated with the exposure mean

Answer 4

• different proportions of people with potential confounder across exposure groups

Question 5

what does not on the causal pathway mean

Answer 5

not the mechanism by which the exposure affects the risk of the outcome

Question 6

impact of confounding :

what is a harmful exposure (over estimating and under estimating)

Answer 6

• confounding resulted in over estimating the true harmful effect of the exposure
  (association appears stronger than it really is, RR is further away from the null)
• confounding resulted in under estimating the true harmful effect of the exposure
  (association appears weaker than it really is, RR is closer to the null)

Question 7

impact of confounding :

what is the beneficial exposure (over and underestimating)

Answer 7

• confounding resulted in overestimating the true protective effect of the exposure
  (association appears stronger than it really is, RR is further away from the null)
• confounding resulted in underestimating the true protective effect of the exposure
  (association appears weaker than it really is, RR is closer to the null)

Question 8

methods for controlling confounding

Answer 8

• randomisation
• restriction
• matching

Question 9

what is randomisation in controlling confounding

Answer 9

randomly allocate into groups

but …..
- only used in RCTs
- works best with large sample size
- need equipoise
- need intention to treat analysis

Question 10

what is restriction in controlling confounding

Answer 10

restrict sample to one stratum of potential confounder

but ……
- can reduce generalisability
- reduces number of potential participants

Question 11

what is matching in controlling confounding

Answer 11

choose people to make the control/comparison groups have the same composition as the case/exposed group regarding the potential confounder

but …..
- individual matching can be difficult and limit number of potential participants

strengths …
- useful for difficult to measure / complex potential confounders
- can improve efficiency of case control studies with small numbers