ABSTRACT
Not all multilevel data are purely hierarchical. For example, pupils are nested within the schools they attend, and within the neighborhoods they live in. Although it is likely that most pupils attend schools in their own neighborhood, there will be some pupils who attend schools in other neighborhoods. It is not possible to set up an unambiguous hierarchy of pupils within schools within neighborhoods. Such data are a cross-classified data structure; pupils are nested within a cross-classification of schools and neighborhoods. This chapter describes cross-classified analysis techniques, and discusses the requirements this poses for the software.
