Types of analytic studies
Limitations of cohort studies
- Can be inefficient with rare/slow to develop outcomes
- Can be inefficient with transient/acute exposures
Alternatives to the limitations of cohort studies
Historical cohort studies
Case-control studies
What issues can case-control studies address that cohort studies can’t?
- Designed for rare/slow to develop outcomes
- Can efficiently examine acute or transient exposures
Cohort studies vs case-control studies
COHORT:
Measure exposure status
Follow over time
Compare development of outcome (incidence)
CASE-CONRTOL
Identify people with outcome
Find people without outcome
Compare exposure likelihood beforehand (odds)
Case-control studies diagram
Logic of case-control studies
Is the exposure more or less likely in people with the outcome (cases) than without (controls)?
Step by step of a CASE CONRTOL study
- Identifying source population
- Identify people with outcome (cases)
- Same people without outcome from the same population (controls)
- Measure exposure prior to outcome in cases and controls
- Compare odds of exposures to calculate measure of association (odds ratio)
In case-control studies what measure of association is used ?
Odds ratio
Why is the odds ratio used
Can’t calculate incidence of outcome
Have selected number of people in study with and without outcome
Odds are not a measure of ……
Occurrence
Odds ratio features
Measure of association
- Ratio of odds instead of incidences
- How many times as likely cases are to have the exposure
compared to controls
Interpretation of the odds ratio vs the relative risk
WHEN A DISEASE IS RARE…
Fortunately… OR ≅ RR
- When disease is rare, OR approximates the RR ( rare disease
assumption)
- Can interpret OR just like RR
Use RR interpretation in this course???? Wtf does that mean?!!!?
Interpreting the odds ratio - 4 key things
- exposed group
- value
- outcome
- comparison group
- use RR interpitation
- Sample people without outcome from same population (controls)
- Measure exposure prior to outcome in cases and controls
Controls don’t have outcome so when do you measure exposure for controls?
Case selection - wtf does any of this mean
Usually try to identify incident cases
Sometimes just recruit people with the outcome ( prevalent cases) Case-control studies defined by outcome
So only one per study
Really important clearly defined and readily identifiable
Control selection
Need to represent the exposure distribution of people without the outcome in the source population
Must be capable of becoming a case
Often select multiple controls per case for statistical power
Exposure measurement
Exposure measurement must be comparable
- dead cases vs alive controls
- interviewers may act differently for cases and controls
- cases trying to work out what made them sick
- outcome may affect recall ability
Case-control studies - approximate____
RR with OR (interpret the same way)
Cohort vs case-control studies
Strengths of case-cotrol study
Strengths:
- Rare outcomes, transient exposures
- Multiple exposures
- Temporal sequencing
- Often comparatively quick and inexpensive
Limitations of case control study
- Usually can only study one outcome
- Difficult to select appropriate control group
- Can be susceptible to selection and recall bias
RCTS and the hierarchy of evidence
