Session #4 Flashcards
observe the outcomes without intervening to affect them
obervational studies
the researcher manipulates the exposure (usually the drug or treatment) to compare it to the standard of care
experimental studies
what are three examples of obervational studies?
- cohort studies
- case-control studies
- cross sectional studies
how are ppl in cohort studies selected?
based on their exposure status
*cohort studies follow participants in time
what is a prospective cohort ?
compares disease prevalence in the exposed and unexposed
what is a retrospective cohort
begin with the exposure of interest and probe back for exposure information
what are the main advantages for cohort studies?
- good for RARE EXPOSURES (not diseases)
- good for calculating INCIDENCE among exposed and unexposed
- -can study multiple diseases
- -minimize error
- -maintains temporal sequence
what is the main disadvantage to cohorts?
inefficient for RARE DISEASES (good for exposures)\
-long follow up
how are subjects selected for case-controlled studies?
-subjects are selected based on their disease status
in case-control studies, cases and controls should be different only in what regard?
past exposure
*theoretically, these should mimic cohort studies
what can case control studies demonstrate?
risk indicators and not risk factors due to retrospective nature of the study design
how are case-control studies set up?
the exposure has to be assessed RETROSPECTIVELY and the proportions of cases and controls who are exposed are unknown at the beginning of the study
*cases and controls must have had an EQUAL CHANCE OF BEING EXPOSED
what is the main advantage for case-control studies?
- good for rare DISEASES
- good for long latency periods
- not expensive
- can evaluate multiple exposures
what is the main disadvantage for case-control study?
- not good for RARE EXPOSURES
- cannot DIRECTLY compute incidence of disease in exposed and non-exposed persons
how are cross-sectional studies set up?
-selection of subjects based on neither exposure or disease status
how are cross-sectional studies set up?
- most basic study design
- “point-in-time” or “snapshot” info
- subject selected without regards to exposure or disease status
- does not need explained etiologic objectives
what are the advant of cross sectional
- sampling and analytic methods provide for statstically valid inference to populations
- exposure and disease are assessed at the individual level
what is the purpose of randomization in RCTs?
to minimize confounding variables
- to create groups that are not determined by another factor other than by chance
- to minimize confounding (known and unknown)
what is the purpose of blinding?
to remove bias or systematic error
what is informed bias?
drawing different conclusions depending on their knowledge of which study arm particular participant is in
selection bias
study recruiters can be eager to recruit “sick ppl” into experimental arm
what is the difference btw systematic reviews and meta analysis?
systematic = complete summary meta-analysis = combined analysis of data from different studies
