Three-Level Models for Clustered Data: The Classroom Example

In this chapter, we illustrate models for clustered study designs having three levels of data. In three-level clustered data sets, the units of analysis (Level 1) are nested within randomly sampled clusters (Level 2), which are in turn nested within other larger randomly sampled clusters (Level 3). Such study designs allow us to investigate whether covariates measured at each level of the data hierarchy have an impact on the dependent variable, which is always measured on the units of analysis at Level 1.