ABSTRACT
In recent years, increasing use has been made of structural equation modeling (SEM) and multilevel modeling to examine the relationships among variables in large-scale data sets. These approaches make it possible to represent, compare, and test models that preserve more realistically the complex nature of intercorrelation and causality that exists in real-world phenomena. The purpose of this chapter is to provide readers with descriptions of these modeling approaches so that when they are encountered in the literature, they will be more accessible. We also hope to encourage researchers in the field of classroom management to consider using these analytic approaches when their data sets are appropriate. Classroom management researchers may also find it helpful to apply these models to answer questions in databases like the National Educational Longitudinal Study (NELS), data compiled by the National Center for Education Statistics (NCES), and other longitudinal data sets. Each section of this chapter will describe models that could be of interest to classroom management researchers or that may be encountered when reading widely in the literature related to classroom management. This chapter will focus on understanding the contexts in which the models might be used and on giving examples of how the models might answer certain types of research questions, rather than technical details of the statistical procedures. References will be provided for further study.
