Critical Thinking - Lecture Twenty-Seven Flashcards
Confounding I
Confounding
A mixing or muddling of effects when the relationship we are interested in is confused by the effect of something else – the confounder
Epi saying for confounding
Risk factors party together
Example given for confounding
If you tend to drink alcohol, you tend to smoker
When if confounding valid?
If groups equivalent for anything else associated with outcome
Three properties of potential confounder
Independently associated with the outcome
Independently associated with the exposure
Not on the causal pathway
Independently associated with the outcome
A risk (or protective) factor for the outcome regardless of exposure status
Independently associated with the exposure
Imbalance in distribution across exposure groups
Not on the causal pathway
Not how the exposure affects the outcome
What can confounding do?
Over/Under-estimatation of a true association, Change the direction of a true association and give appearance of an association when not one
Give appearance of an association when not one
Go from null to something else
Change direction of a true association
Risk factor becomes protective factor (and vice versa)
Harmful exposure: over-estimation
Confounding has resulted in an over-estimation of the true harmful effect of the exposure (association appears stronger than it really is, RR is ‘further away from the null’)
Harmful exposure: under-estimation
Confounding has resulted in an under-estimation of the true harmful effect of the exposure (association appears weaker than it really is, RR is ‘closer to the null’)
Beneficial exposure: over-estimation
Confounding has resulted in an over-estimation of the true protective effect of the exposure (association appears stronger than it really is, RR is ‘further away from the null’)
Beneficial exposure: under-estimation
Confounding has resulted in an under-estimation of the true protective effect of the exposure (association appears weaker than it really is, RR is ‘closer to the null’)
Identifying potential confounders
Collect information on all potential confounders and look for imbalance in potential confounder between groups
Criterion of collecting information on all potential confounders
Use literature to identify known and suspected risk factors for outcome
Collect information on factors strongly associated with exposure, regardless if known risk factor
Why collect information on all potential confounders
If you don’t measure it, difficult to do anything about it later
What do randomisation, restriction and matching have in common?
All attempt to make groups being compared alike with regard to potential confounder(s)
Can’t assess association between potential confounder and outcome
Can’t assess whether actually a confounder
When is randomisation used?
In randomised controlled trials
Limitations of randomisation?
requires large sample size, needs equipoise and needs intention-to-treat analysis
Restriction
Restrict sample to one stratum of potential confounder
When is restriction used?
Can be applied to all study designs
Limitations of restriction
Can reduce generalisability, reduces number of potential participants, potential for residual confounding with imprecisely measured (or broadly defined) confounders and usually only one potential confounder
Matching
Choose people for the comparison (control) group who have the same values of the potential confounding factor(s) as people in the exposed group (cohort studies) or case group (case-control studies)
When is matching used?
Usually in case-control studies; individual or frequency
Individual matching
Ratio of cases to controls
Frequency matching
Assure that cases and controls have the same distributions
Positives of matching
Useful for difficult to measure/complex potential confounders and can improve efficiency of case-control studies with small numbers
Limitations of matching
Individual matching can be difficult and limit number of potential participants and need special matched analysis for individual matching
