What is bias
…any systematic error in an epidemiologic study that results in an incorrect estimate of the association between exposure and risk of disease.
What happens when we have systematic error
Findings could be:
• Over-estimated
• Under-estimated
• Not affected
When can selection and information bias be controlled?
• Selection and information bias can only be controlled during the design and data collection phases of a study
Selection bias
“ …occurs when there is a systematic difference between the people who are included in a study and those who are not, or when study and comparison groups are selected inappropriately or using different criteria”
Minimising loss to follow-up to reduce systematic error
- Alternative contact details obtained at the start of the study
- Maintaining regular contact e.g. study newsletters
- Making several attempts to contact people
Are all study designs susceptible to bias? All to the same level?
“ While all analytic studies are subject to bias, each design has particular types to which it is inherently most vulnerable”
Considering selection bias - three questions to ask
- Who entered the study?
- Is the sample representative of the source population?
- What is the response rate?
S election bias: Cross-sectional studies
- three things to think about
- Who entered the study?
- Is the sample representative of the source population?
- What is the response rate?
Selection bias: Case-control studies - how does it arise
Participants are selected on the basis of their outcome status. If this selection is in some way dependant on their
exposure status then bias can occur
Exposure and outcome have already occurred
Cases and controls are selected separately
Selection of cases and controls must be independent of the exposure status
Selection of cases and controls must be independent of the ______
Selection of cases and controls must be independent of the exposure status
case - control study - how do you reduce bias
Ensure the identification or participation of cases is NOT related to exposure status
- Ensure high participation
- Clearly defined population of interest
- Reliable way of ascertaining all cases or a representative sample of cases
Potential biases in selection of controls
- If controls are not representative of the population which gave rise to cases (in place or time)
- If inclusion/exclusion criteria differ between cases and controls
- If non-participation of eligible controls
Hypothetically, what if its easier to find a case who has the exposure????
Cohort studies - what is the main cause of selection bias?
Loss to follow up
• If loss to follow-up is related to both the exposure and the
outcome this can lead to bias
For loss to follow up to cause bias in cohort studies, what needs to happen?
• If loss to follow-up is related to both the exposure and the
outcome this can lead to bias
Two key ways selection bias occurs in cohort studies
- If comparison group selected separately from exposed group can lead to bias
- loss to follow up
RCT bia?
Loss to follow up
