1. COHORT VS. CASE-CONTROL STUDIES
Adriana Pérez Fortis

2. OVERVIEW
 What is a cohort study?
 Types of cohort studies
 Advantages / Disadvantages
 What to look in cohort studies?
 What is a case-control study?
 Advantages / Disadvantages
 What to watch out for in case-
control studies?

3. What is a cohort study?
A cohort study tracks two or more groups
forward from exposure to outcome.

4. What is a cohort study?
Compares the experience of a group exposed to some
factor with another group not exposed to the factor.
If the former group has a higher or lower frequency of an
outcome than the unexposed, then an association
between exposure and outcome is evident.

5. Types of cohort studies
Prospective cohort design
Allows exposure to risk factors to be assessed
directly and confounding variables to be considered.
Retrospective cohort design
Is effective for diseases with a long development
time. Sometimes referred to as historical cohort
studies, they offer the advantage of speed and low
cost compared to a prospective cohort.

6. Cohort studies
Advantages Disadvantages
 The best way to ascertain both  Selection bias is built into cohort
the incidence and natural history studies.
of a disorder.
 Is not optimum for rare diseases
 Are useful in investigation of or those that take a long time to
multiple outcomes that might develop.
arise after a single exposure.
 Loss to follow-up can be a
 Are also useful in the study of difficulty. Differential losses to
rare exposures. follow-up between those exposed
and unexposed can bias results.
 Reduce the risk of survivor bias.
 Can be expensive and time
 Allow calculation of incidence
consuming.
rates, relative risks, and
confidence intervals.

7. What to look in cohort studies?
a. Who is at risk? How much selection bias
was present?
b. Who is exposed?
What steps were taken to
c. Who is an appropriate minimize information bias?
control?
How complete was the
d. Have outcomes been follow-up of both groups?
assessed equally?
Were potential confounding
e. Have losses been factors sought and
minimized? controlled for in the
analysis?

9. What is a case-control study?
Is an analytical observation study, which has a
comparison (control) group.
Case control studies are retrospective, and the
main objective is to determine whether or not an
association exists between a disease and a
particular risk factor.

10. What is a case-control study?
They should not be confused with historical cohort
studies (also retrospective).
Case control studies trace backwards from
outcome to exposure.
Cohort studies: Study Case-control studies:
groups are defined by Study groups are defined
exposure. by outcome.

11. Case-control studies
Advantages Disadvantages
 Is the most efficient design in  If the frequency of exposure is
terms of time, money, and effort. low, case-control studies quickly
become inefficient.
 Are also efficient in the
investigation of diseases that have  Many methodological issues
a long latency period. affect the validity of the results of
case-control studies.
 Are useful to study rare
diseases.  Are prone to selection and recall
bias.
 Can study multiple risk
factors/exposures.  It can be difficult to choose an
appropriate control group.
In general cohort studies can be more efficient than
case-control studies.

12. What to watch out for in case-control studies?
Selection of case and control groups.
 Researchers should detail eligibility criteria used for
selection.
 Controls should represent the population at risk of
becoming cases.
 Selection of controls must be independent of the exposure
being investigated.

13. What to watch out for in case-control studies?
Measurement of exposure information.
 Participants, might inaccurately remember past exposures,
especially those that happened a long time ago.
 This differential recall (recall bias) causes information bias.
 Differential recall between cases and controls led to a biased
estimate of risk.
 Investigators who do case-control studies must be aware of
the potential for information bias.
 Reports of case-control studies that do not detail use of
memory aids, should make readers skeptical.

14. What to watch out for in case-control studies?
Control for confounding.
 Case-control studies need to address confounding bias.
 Invalid measurement of potential confounding factors leads
to residual confounding, even after adjustment.

17. REFERENCES
Grimes, D. A., & Schulz, K. F. (2002). Cohort studies: marching
towards outcomes. The Lancet 359, 341-345.
Schulz, K. F., & Grimes, D. A. (2002). Case-control studies:
research in reverse. The Lancet 359, 431-434.