Study Design Key

Below is a list of definitions that correlate with study designs assigned by the accompanying taxonomy. At the end of this list are some additional concepts that may be useful during study design classification.

Non-randomized trial

A study in which individuals or groups of individuals (e.g., community, classroom) are assigned to the intervention or control by a method that is not random (e.g., date of birth, date of admission, judgement of the investigator). Individuals or groups are followed prospectively to assess differences in the outcome(s) of interest. The unit of analysis is the individual or the group, as appropriate.

Randomized trial

A study designed to test the efficacy of an intervention on an individual, a group of individuals, or clusters (e.g., classrooms, communities). Individuals or clusters are randomly allocated to receive an intervention or control/comparison (e.g., placebo or another intervention) and are followed prospectively to assess differences in outcomes. The unit of analysis is the individual, group of individuals, or the cluster, as appropriate. Variations in treatment assignment and measurement produce different types of studies including factorial, cross-over, parallel, stepped wedge and Solomon four-group.

Prospective cohort study

A study in which individuals in the group without the outcome(s) of interest (e.g., disease) are classified according to exposure status at baseline (exposed or unexposed) and then are followed over time to determine if the development of the outcome of interest is different in the exposed and unexposed groups.

Retrospective cohort study

A study in which a group of individuals is identified on the basis of common features that were determined in the past. The group is usually assembled using available data sources (e.g., administrative data). Individuals are classified according to exposure status (exposed or unexposed) at the time the group existed and are followed up to a prespecified endpoint to determine if the development of the outcome of interest is different in the exposed or unexposed groups.

Interrupted time series with comparison group

A study in which multiple observations over time are “interrupted” by an intervention or exposure and in which two series are examined (one is a comparison group). There must be at least 3 observations before and at least 3 observations after the intervention or exposure for each group. The investigator(s) does not assign or have control over the intervention/exposure, which may be an environmental variable (e.g., airborne toxin) or administrative assignment (e.g., seatbelt legislation, educational program, service delivery model) but does have control over the timing of the measurement and the variables being measured.

Controlled before-after study

A study in which the outcome(s) of interest is measured both before and after the intervention or exposure in two or more groups of individuals. In this study design the study group receives the intervention or exposure and the comparison group(s) does not. This type of study includes interventions that may be in the control of the investigator (e.g., a surgical procedure) as well as interventions that may be an environmental variable (e.g., airborne toxin) or administrative assignment (e.g., seatbelt legislation). In all cases the investigator(s) has control over the timing of the measurement and the variables being measured.

Non-concurrent cohort study

A study in which 2 or more groups of individuals are identified on the basis of common features at different time points. Individuals in each group are classified according to exposure status (exposed or unexposed) at the time the groups existed or were created. They are followed to determine if the development of the outcome of interest is different in the exposed or unexposed groups.

Nested case control study

A study where exposed and control subjects are drawn from the population of a prospective cohort study. Baseline data are obtained at the time the population is identified; the population is then followed over a period of time. The study is then carried out using persons in whom the disease or outcome has developed and a sample of those who have not developed the outcome of interest (controls).

Case control study

A study in which participants are selected based on the known outcome(s) of interest (e.g., disease, injury). Exposure status is then collected based on the participants' past experiences. Exposure status is compared between the two (or more) groups: those who have the outcome of interest and those who do not have the outcome of interest (controls). This is a retrospective study that collects data on events that have already occurred.

Interrupted time series (without a comparison group)

A study in which multiple observations over time are “interrupted” by an intervention or exposure. There must be at least 3 observations before the intervention and at least 3 observations after the intervention; otherwise, the study is considered a before-after study. The investigator(s) does not assign or have control over the intervention/exposure, which may be an environmental variable (e.g., airborne toxin) or administrative assignment (e.g., seatbelt legislation, educational program, service delivery model) but does have control over the timing of the measurement and the variables being measured.

Before-after study

A study of an intervention or exposure in which the investigator(s) compares the outcome(s) of interest both before and after the intervention in the same group of individuals. This includes interventions that may be in the control of the investigator (e.g., a surgical procedure) as well as interventions that may be an environmental variable (e.g., airborne toxin) or administrative assignment (e.g., seatbelt legislation). In all cases the investigator(s) has control over the timing of the measurement and the variables being measured.

Cross-sectional study

A study in which both the exposure and the outcome status in a target population are assessed concurrently, that is, at the same point in time or during a brief period of time. The temporal sequence of cause and effect cannot necessarily be determined. They are most commonly used to assess prevalence. A common method for data collection is a survey.

Non-comparative study (case series)

Examples of this design include:

• A study that presents a description of a single patient or participant. Studies are usually retrospective and typically describe the manifestations, clinical course, and prognosis of the individual.
• A study that describes the experience of a group of patients with a similar diagnosis and/or treatment. Studies are usually retrospective and typically describe the manifestations, clinical course, and prognosis of a condition.
• A study in which data are collected at a series of points in time on the same population to observe trends in the outcome(s) of interest.

Additional Concepts

Cluster

The term ‘cluster’ refers to a unit of allocation or analysis in a clinical trial. Examples of clusters include hospitals, schools, neighborhoods, or entire communities.

Cluster randomized controlled trial

Synonym: community trial; group randomized trial

A randomized controlled trial in which the units of randomization and analysis are groups of people or communities (e.g., classroom, hospital, town). Typically, several communities receive the intervention and several different communities serve as controls.

Cohort

The term ‘cohort’ refers to a group of individuals (or other organizational units) who have a common feature when they are assembled (e.g., birth year, place of employment, medical condition, place or time period of medical treatment) and are followed over time. They can be followed prospectively or examined retrospectively.

Experimental study

A type of study in which investigators have direct control over the timing, course, and assignment of the intervention. Experimental studies investigate an intervention to determine its effect on the outcome(s) of interest. In an experimental study a population is selected to receive a specific intervention the effects of which are measured by comparing the outcomes in the experimental group with the outcomes of a control group that has received another intervention or placebo. Examples include randomized controlled trial, cluster randomized controlled trial, nonrandomized trial, n-of-one trial. See also observational study.

Observational study

A study in which the investigator(s) does not control the exposure/intervention status of study participants (i.e., the assignment of the intervention or exposure of interest is not under the control of the investigator(s)). The simplest form of observational study is the case report or case series, which describes the clinical course of individuals with a particular condition or diagnosis. Observational studies include descriptive and analytic studies. See also experimental study.

Quasi-experimental study

A type of study in which the investigator(s) evaluates the effect of an intervention but does not have full control over the timing, course, or allocation of the intervention. They are often used when it is not possible to conduct a true experimental study.