Epidemiological study design Flashcards
Type of observational study that:
Often provide info about rare occurrences, can help identify new trends or diseases
Case report/series
Type of observational study that:
Examines relationship between exposure and disease with population-level data
Ecological/correlation study
Phenomenon where absence of individual cause and effect may lead to faulty associations
Ecological fallacy
Type of observational study that:
Examines relationship between exposure and disease prevalence in a defined population at a single point in time (“Snapshot study”)
Cross-sectional (prevalence survey)
Type of observational study that:
Compares group with disease to group without disease and looks for prior exposure or risk factor
“What happened?”
Case control (retrospective) studies
Type of observational study that:
Exposure information is collected at the start of the study and the new cases of disease are identified
“Watch and wait”
Can measure incidence
Cohort (longitudinal or prospective) studies
Observational study that is a “snapshot study”
Cross sectional
Observational study that looks at “What happened?”
Case-control studies
Observational study that is a “Watch and wait”
Cohort studies
Experimental study type that is good if effect is permanent or long-lasting
Randomized controlled studies
Experimental study type that is preferred format if effect is of short duration
Crossover studies
Subset of selection bias that arises from evaluating data on biased patients and hospital records only (not a good sample of the population)
Berkson bias
Berkson bias is a subset of this type of bias
Selection bias
(Arises from evaluating data on biased patients and hospital records only (not a good sample of the population))
Loss to follow up is a subset of this type of bias
Selection bias
Healthy worker/volunteer is a subset of this type of bias
Selection bias
Recall bias is typically associated with this type of study
Case control studies
Refers to the fact that some subjects will alter their behavior when they know they are being studied
Hawthorne effect
Hawthorne effect is a subset of this type of bias
Measurement (performing bias)
(Refers to the fact that some subjects will alter their behavior when they know they are being studied)
Subset of performing bias where participants in different groups are not treated the same
Procedure bias
Subset of performing bias where the researcher inadvertently conveys his expectations regarding his expectation of the result (“self-fulfilling prophecy”)
Observer-expectancy bias (Pygmalion effect)
Recall bias, Measurement, Procedure bias, and Observer-expectancy bias are subsets of this type of bias
Performing bias
Subset of interpreting results bias where association between exposure and outcome is distorted by an extraneous third variable
Confounding
Subset of interpreting results bias where early detection looks like an increase in survival
Lead-time
Subset of interpreting results bias where screening test identifies disproportionate number of slowly progressing diseases but misses rapidly progressing diseases
Length
Study design at the top of the evidence pyramid where multiple studies summarized with selection based on predetermined criteria
Systematic review
Study design at the top of the evidence pyramid that pools data from several studies using statistical analysis to estimate treatment effect
Meta-analysis
Observational studies used when there is no comparison group available
Case report/series and ecological/correlational design
Observational study where exposure is known, and outcome is studied
Cohort study
Observational study where outcome is known, and exposure is studied
Case-control
Observational study where exposure and outcome are known
Cross-sectional
