Evidence-Based Practice for Nurses

Case-Control Studies

Case-control studies are designed to sample a group of
people with and a group of people without the disease or
the outcome measure being studied. Individuals are asked
to recall their past exposures to risk factors associated
with the disease. Because individuals are recalling their
past, these designs are retrospective designs. Individuals
who have the disease are known as cases. Those individuals who do not have
the disease of interest but who are at risk for developing the disease are known
as controls. Cases are often asked to recall exposures up to 1 year prior to
diagnosis. Controls are asked about their history of exposures up to the point
of entry into the study.

In a case-control study, the investigator compares the probability of exposure
for persons who have the disease to the probability of exposure for persons
who do not have disease. The statistical test used for a case-control study is
the odds ratio (OR). For example, the Mississippi Department of Health was
interested in examining the relationship between smoking and heart disease.
Investigators examined medical records at Jackson County Hospital and invited
500 patients who had experienced an AMI to join the case-control study. Then
they contacted 500 people from Jackson County who did not have a history
of heart disease but who were similar to the cases in all other demographic
areas. The investigators asked the cases to recall their exposures 1 year prior to
diagnosis and asked the controls to recall their exposures up to the date of the
interview. The investigators found that 400 of the cases were current smokers
compared to 150 controls who were smokers. In a 2 × 2 table, the data are
expressed as follows:

AMI (Cases)

No AMI

(Controls) Total

Smoking 400 150 550

No Smoking 100 350 450

Total 500 500 1,000

The investigators, using the 1,000 participants, calculated an OR using the
following formula:

OR==()400 350150 100()==140,00015,000 9.33

()()

ad

bc

The value of an OR is interpreted by comparing it to 1.0. When an OR is
equal to 1.0, the probability of disease among the exposed and the nonexposed

KEY TERMS

case-control: A type

of retrospective

study in which

researchers begin

with a group

of people who

already have the

disease; studies

that compare two

groups: those who

have a specific

condition and those

who do not have

the condition

odds ratio:

The statistic

reported when

epidemiologists

conduct a

case-control study

FYI

Researchers use analytic study designs to

test hypotheses and to test the association

between exposure and disease. These types

of studies include case-control studies, cohort

studies, and intervention studies.

8.6 Analytic Study Designs 209