Randomized Controlled Trial A group of patients is randomized into an
Experimental group and a Control group. These groups are followed for variables and outcomes of interest.
Randomization of the two groups is accomplished by making assignments from a table of random numbers,
using calculator programs that generate random numbers, or even drawing numbers from a hat; but, for true
random assignment to take place, each subject must have an equal chance of being assigned to any of the
study groups at hand. Effective randomization ensures the two groups are similar in all important respects
except the intervention.
Cohort Involves identification of two groups (cohorts) of patients, not chosen
randomly but patients who fall into one group or another by nature or choice—one which received the
exposure of interest and the one which did not. Cohorts are followed forward for the outcome of interest.
Smokers versus non-smokers.
Inception Cohort Cohort study which begins at the same point in time with the
exposure of interest such as patients who appear in an Emergency Room with Myocardial Infarctions followed
forward in time for morbidity.
Case-Control A study which involves identifying patients who have the outcome
of interest (cases) and control patients without the same outcome. Looking back in time to see if they
have the exposure of interest such as looking at patients with leukemia and comparing their exposure to
power cables to those who do not have leukemia.
Survey The observation of a defined population at a single point in time.
Exposure and outcome are determined simultaneously. This slice-in-time design is also referred to as a
prevalence survey, because its population basis makes it possible to estimate the frequency of disease
within a group. For example, a national telephone survey of US adults that compares the use of medical
services, such as routine check-ups and preventive services according to health insurance status.
