1180-1181 / 1676
FMB
Cohort study (observational, longitudinal, forward, incidence)
Case-control (observational, retrospective, case-referent)
Cross-sectional (single time point, prevalence)
Epidemiological study design
Exposure
Disease
?
?
Time
Exposure
Disease
?
?
Historical data
Exposure
Disease
Time 1 population cross-section
Exposure
Disease
Time N population cross-section
clean design (e.g. eligibility, standards)
time of event and directionality
multiple endpoints
! confounders
! Lost to follow-up
! not always feasible (rare disease)
! expensive
quick
cheap
sample size
feasible for rare disease or diseases with
long latent time
! prone to bias (e.g. recall)
! not observational (reliant on records)
quick
cheap
easy (e.g. ethics)
! association, not causality
! prone to bias (e.g selection)
! unbalanced
! confounders