← All notes
Community Medicine (PSM)Epidemiologyhigh-yield

Study designs and the biases that break them

The hierarchy of study designs from case report to meta-analysis, which measure each yields, and the classic biases to name in the exam.

6 min read · updated 2026-08-24

The ladder of evidence

Designs are ranked by how well they defend against bias and confounding. Climb the ladder and control improves; the strongest observational design still cannot match a randomised trial for causation.

DesignWhat it doesDirectionMeasureKey strength / weakness
Case report / seriesDescribes one or a few patientsNoneHypothesis-generating only; no comparison group
Cross-sectionalExposure and disease measured at one pointSnapshotPrevalence, prevalence ratioFast, cheap; cannot tell which came first
Case-controlStart with disease, look back at exposureBackwardOdds ratio (OR)Good for rare diseases; prone to recall & selection bias
CohortStart with exposure, follow to outcomeForwardRelative risk (RR), incidenceGives incidence & temporality; slow, costly, loss to follow-up
RCTRandomly allocate exposure/treatmentForwardRR, risk differenceRandomisation controls known and unknown confounders
Meta-analysis / systematic reviewPools multiple studiesPooled OR/RRTop of the pyramid; only as good as its inputs (garbage in, garbage out)

OR versus RR — the trap

You cannot calculate relative risk from a case-control study because incidence is unknowable when you have hand-picked the cases. Case-control gives an odds ratio; cohort and RCT give relative risk. When disease is rare, OR approximates RR — the exam's favourite rare-disease assumption.

Biases worth naming

BiasWhere it bitesOne-line tell
Selection biasCase-control, cross-sectionalStudy group not representative (e.g. Berkson's, healthy-worker effect)
Recall biasCase-controlCases remember exposures better than controls
Lead-time biasScreeningEarlier diagnosis lengthens apparent survival without changing death date
Length-time biasScreeningScreening preferentially catches slow, indolent disease
ConfoundingAll observationalA third factor linked to both exposure and outcome (age, smoking)

Randomisation defeats confounding; blinding defeats observer and information bias; a prospective design defeats recall bias.

Anchor: Case-control → odds ratio, looks backward, best for rare disease. Cohort/RCT → relative risk, looks forward. Screening's two con-artists are lead-time and length-time bias.

Sources

  • Park's Textbook of Preventive and Social Medicine, 27e
  • Gordis Epidemiology, 6e