Obstetrics and Gynecology Board Review Pearls of Wisdom

••• CHAPTER 64^ Basic Epidemiology and Clinical Biostatistics^647

❍ Describe the various types of observational studies.
An observational study may be forward looking (cohort), backward looking (case-control), or looking at
simultaneous events (cross-sectional). Cohort studies generally provide stronger evidence than case-control or
cross-sectional study designs. Historical cohort studies are retrospective cohort studies of data collected in the past.
Observational studies cannot establish cause and effect.
Cross-sectional study: An observational study that examines a characteristic in a group of subjects at one point in
time (provides a “snap-shot” in time). For example, surveys and studies to describe the prevalence of disease and/
or exposure in a specific population at one point in time are cross-sectional studies.
Case-control study: A type of study that examines patients who have the outcome or disease of interest and
compares them to control subjects who do not have the outcome or disease.
Cohort study: A longitudinal study composed of two groups of people; one group having a risk factor or exposure,
and the other group who do not have the risk factor or exposure. Both groups are followed prospectively
through time to learn how many people in each group develop the outcome or consequence of interest.

❍ Describe an experimental (intervention) study.
An experimental study is a comparative study involving an intervention or manipulation. RCTs are examples
of experimental studies. Subjects with the disease or problem of interest are randomly assigned to the treatment
or control group. Comparisons between the groups are made for any differences in the outcome of interest as a
result of the intervention (treatment). It is the most robust design for investigating a causal relationship between a
treatment and its effect.

❍ What is a box plot?
A box plot is a graph that displays both the frequencies and distributions of observations.
It is useful for comparing two distributions. It is also called a “box and whisker” plot.

0 10 20

Lower

Extreme Median

Lower

Quartile Upper

Extreme

Upper

Quartile

30 40 50 60 70 80 90 100

❍ Define frequency distribution.
In a set of numerical observations, the list of values occurs along with the frequency of their occurrence. It can be
displayed as a graph or table. Frequency distributions are used to condense the data into a more manageable form.

Height (cm) Frequency

170 7

172 2

174 3

176 1

178 4