Bias, confounding and causation
Selection and information bias, confounding, effect modification and the criteria for causation.
17 pages
Measure
Bias
- Attrition biasIf the people who drop out of a study differ between groups, the result among those who stay can…
- ConfoundingA third factor, linked to both exposure and outcome, creates or hides an association that is not…
- Information (measurement) biasIf exposure or disease is measured badly, people land in the wrong box and the association is…
- Observer bias and the Hawthorne effectKnowing who is in each group changes how things are measured; feeling watched changes how people…
- Recall biasPeople who are ill tend to search for and remember their past exposures more than healthy people…
- Selection biasIt happens when the people who get into or stay in a study do not represent the population of…
- Spectrum biasA diagnostic test looks better than it is when it is tried only on very sick and clearly healthy…
- Verification (work-up) biasIf only people who test positive get the reference test, sensitivity looks higher and…
Concept
- Bradford Hill criteria for causationNine viewpoints, proposed in 1965, for judging whether an association is causal
- Causal models: necessary, sufficient and component causesAlmost no disease has a single cause: several pieces act together
- Chance, bias, confounding or causeWhen two things show up together in a study there are four possible explanations
- Controlling confoundingConfounding can be prevented when designing a study (chance, restriction, matching) or corrected…
- Effect modification (interaction)The exposure has a different effect depending on a third factor (age, sex, genes)
- Gene-environment interactionAn exposure harms people with a certain gene variant far more, or a gene only causes disease…
- Internal and external validityInternal: whether the result is true for those who took part
- Reverse causationSometimes the exposure does not cause the disease; the disease (or its first symptoms) changes…
A to Z
← Epidemiology, biostatistics and public health
Educational content on epidemiological and statistical methods; the examples use made-up numbers to teach the calculation. Not a clinical or legal guide: current Colombian rules are in the official sources.
Representative model, for educational purposes only.