Nested Design

TL;DR

Levels of an independent variable are organized so they are related or overlap rather than independent.
Enables comparisons of multiple levels while controlling for other variables by comparing within related groups.
Can allow analysis of several levels with a relatively small sample size.

Definition

Nested design, also known as hierarchical design or multilevel design, is a type of experimental design in which the levels of an independent variable are nested within each other. This means that the levels of the independent variable are not independent of one another, but rather they are related in some way.

Explanation

In a nested design the levels of an independent variable are arranged so that members at one level are contained within, or overlap with, members at other levels. Because the levels are related, researchers can compare effects while controlling for variables that might otherwise confound results (for example, background characteristics or prior knowledge). Nested designs are described as hierarchical or multilevel because of this layered relationship among levels.

The structure permits within-group comparisons that help isolate the effect of the independent variable. It also makes it possible to compare multiple levels of the independent variable while maintaining a relatively small sample size, since the same participants or units may contribute information to more than one level. Nested designs additionally help control for variables that may be correlated with the independent variable.

Examples

Teaching methods example

One example of nested design is a study that examines the effect of different teaching methods on student achievement. In this study, the independent variable is the teaching method, and the levels are traditional, online, and blended. The traditional teaching method is when the teacher delivers the material in a traditional classroom setting, the online method is when the material is delivered online, and the blended method is when the material is delivered both online and in the classroom.

Each level of the independent variable is nested within the other, meaning that each student in the traditional group will also be in the online group and the blended group. This allows the researchers to compare the effect of each teaching method on student achievement while controlling for other variables, such as the student’s background and prior knowledge.

Exercise types example

Another example of nested design is a study that examines the effect of different types of exercise on weight loss. In this study, the independent variable is the type of exercise, and the levels are cardiovascular, strength training, and a combination of both. The cardiovascular group only does cardiovascular exercise, the strength training group only does strength training, and the combination group does both types of exercise.

Again, each level of the independent variable is nested within the other, meaning that each participant in the cardiovascular group will also be in the strength training group and the combination group. This allows the researchers to compare the effect of each type of exercise on weight loss while controlling for other variables, such as the participant’s diet and lifestyle.

Hierarchical design
Multilevel design