lecture 4: study designs Flashcards
observe the outcomes without intervening to affect them
observational study
The researcher manipulates the exposure (usually a drug or treatment) to compare it to the standard of care
Experimental studies
types of observational studies
cohort
case control
cross-section
Subjects are selected based their exposure status
Cohort studies
compares disease prevalence in the exposed and unexposed
Prospective cohort
begin with the exposure of interest and probe back for exposure information
Retrospective cohort
disadvantages of cohort studies
expensive
Inefficient for rare diseases
long follow up
Diagnostic trends
Subjects are selected based on their disease status
Case-Control Studies
Cases and controls should be different only on their past exposure
Case-Control Studies
Can demonstrate risk indicators and not risk factors due the retrospective nature of the study design
Case-Control Studies
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
Case-Control Studies
must have had an equal chance of being exposed case-control studies
cases and controls
Efficient for rare diseases
Case-coontrol studies
Inefficient for rare diseases
cohort studies
allow for the evaluation of multiple exposures that may increase risk for a specific disease
case-control
Cannot directly compute incidence of disease in exposed and non-exposed persons
case-control studies
Not optimal for rare exposures
case-control studies
selection of subjects based on neither exposure or disease status
Cross-sectional Studies
Most basic study design
Cross-sectional Studies
Subject selected without regards to exposure or disease status
Cross-sectional Studies
point-in-time” or “snapshots” information
Cross-sectional Studies
Does not need explained etiologic objectives
Cross-sectional Studies
Sampling and analytic methods provide for statistically valid inference to populations
advantages of cross sectional studies
Exposure and disease are assessed at the individual level
advantages of cross sectional studies
Temporality cannot be assessed
Cross-sectional Studies
Randomized clinical trial and Community intervention trials
Experimental studies
typical type of study used in clinical medicine
Randomized Clinical Trial (RCT)
Are sub-types of cohort studies in which exposure (i.e., treatment) is randomly assigned by the investigator
Randomized Clinical Trial (RCT)
The process by which each participant’s treatment is determined by some random mechanism
randomization of RCT’s
minimizes confounding (known and unknown) results
randomized RCT’s
create groups (experimental and control) that are not determined by any other factor other than by chance
using randomized RTC’s
the investigator and/or the participant do not know what arm the participant is in
blinding in RCT’s
the participant does not know but investigator does know treatment assignment
single blinded
where neither participant nor investigator know treatment assignment
double blinded
purpose of blinding
to remove bias or systematic error
drawing different conclusions depending on their knowledge of which study arm particular participant is in
Information bias
study recruiters can be eager to recruit “sick persons” into experimental arm
Selection bias
Considerations in experimental studies
Stopping rules
Sample size
Analysis and Interpretation
systematic complete summary of the literature
Systematic Review
combined analysis of data from different studies following strict guidelines
Meta-analysis
