ABSTRACT
In the social sciences, much of the data that we deal with are hierarchical in nature. Examples of naturally occurring hierarchies include students nested within schools, patients nested within hospitals, workers nested within companies, husbands and wives nested within couple dyads, and observations nested within people. Most traditional statistical analyses assume that observations are independent of each other. The assumption of independence means that subjects’ responses are not correlated with each other. This assumption might be reasonable when data are randomly sampled from a large population. However, when people are clustered within naturally occurring organizational units (e.g., schools, classrooms, hospitals, companies), the responses of people from the same cluster are likely to exhibit some degree of relatedness with each other, given that they were sampled from the same organizational unit. Hierarchical linear modeling allows researchers to adjust for and model this nonindependence.
