Guest Lecture – Tashiyana Devanathan
Study designs: Case control and Cohort
Introduction/ Recap
Study designs are structured approaches to address specific research questions- looks
at the relationship between exposure and outcome to answer a research question.
Outcomes- Health outcome of interest in the study- Disease, death, side effect,
complication (stats: “dependent variables” Y axis)
“Exposures”- Measures that may be associated with the outcome - Possible “risk
factors”, “causes”, “determinants” (stats: “independent variables” X axis)
Already familiar with cross-sectional which looks at exposure and outcome
simultaneously, today’s focus on case-control and cohort study designs.
Case-control study design
You have the outcome, you are investigating exposure
In order to do this: Compares a group of participants possessing a condition of interest
(cases) to a similar group who do not possess that condition of interest (controls)-
Those who have the outcome compared to those who don’t.
The case group is chosen because they already possess the attribute of interest
(disease, condition, complication)- outcome
The point of a control group is to facilitate investigation whether the case group is
more likely to exhibit the outcome than the controls.
, The control group should have similar demographic characteristics to the case group
except for the outcome being investigated in order to produce the most accurate
results.
More controls= more accurate results
The same set of questions is asked to both groups in order to investigate exposure
related to the outcome.
This is a good way of looking for risk factors for a disease.
Example: To investigate if smoking is associated with an increased risk of lung cancer.
Cases: Patients who have been diagnosed with lung cancer (the outcome of interest).
Controls: Patients who do not have lung cancer but are otherwise similar in age,
gender, and other relevant factors.
Exposure Assessment: Gather information on the smoking history of both the cases
and controls, such as whether they have smoked, for how long, and how much.
Analysis: Compare the frequency of smoking between the cases and controls. If
smoking is more common among the cases than the controls, it may suggest an
association between smoking and lung cancer.
Draw a conclusion based on your results- is the exposure related to the outcome?
Advantages of case-control studies:
Good design for rare, chronic and long latency diseases
Relatively inexpensive (population size and time)
Allows for the examination of multiple exposures
Estimate odds ratios
Hospital-based studies and outbreaks
Disadvantages of case-control studies:
Multiple outcomes cannot be studied
Recall bias
Sampling bias
Study designs: Case control and Cohort
Introduction/ Recap
Study designs are structured approaches to address specific research questions- looks
at the relationship between exposure and outcome to answer a research question.
Outcomes- Health outcome of interest in the study- Disease, death, side effect,
complication (stats: “dependent variables” Y axis)
“Exposures”- Measures that may be associated with the outcome - Possible “risk
factors”, “causes”, “determinants” (stats: “independent variables” X axis)
Already familiar with cross-sectional which looks at exposure and outcome
simultaneously, today’s focus on case-control and cohort study designs.
Case-control study design
You have the outcome, you are investigating exposure
In order to do this: Compares a group of participants possessing a condition of interest
(cases) to a similar group who do not possess that condition of interest (controls)-
Those who have the outcome compared to those who don’t.
The case group is chosen because they already possess the attribute of interest
(disease, condition, complication)- outcome
The point of a control group is to facilitate investigation whether the case group is
more likely to exhibit the outcome than the controls.
, The control group should have similar demographic characteristics to the case group
except for the outcome being investigated in order to produce the most accurate
results.
More controls= more accurate results
The same set of questions is asked to both groups in order to investigate exposure
related to the outcome.
This is a good way of looking for risk factors for a disease.
Example: To investigate if smoking is associated with an increased risk of lung cancer.
Cases: Patients who have been diagnosed with lung cancer (the outcome of interest).
Controls: Patients who do not have lung cancer but are otherwise similar in age,
gender, and other relevant factors.
Exposure Assessment: Gather information on the smoking history of both the cases
and controls, such as whether they have smoked, for how long, and how much.
Analysis: Compare the frequency of smoking between the cases and controls. If
smoking is more common among the cases than the controls, it may suggest an
association between smoking and lung cancer.
Draw a conclusion based on your results- is the exposure related to the outcome?
Advantages of case-control studies:
Good design for rare, chronic and long latency diseases
Relatively inexpensive (population size and time)
Allows for the examination of multiple exposures
Estimate odds ratios
Hospital-based studies and outbreaks
Disadvantages of case-control studies:
Multiple outcomes cannot be studied
Recall bias
Sampling bias
