Structural equation modeling can be easily understood if the researcher has a grounding in basic statistics, correlation, and regression analysis. The rst three chapters provide a brief introduction to structural equation modeling (SEM), basic data entry, and editing issues in statistics, and concepts related to the use of correlation coefcients in structural equation modeling. Chapter 4 covers the essential concepts of SEM: model speci-cation, identication, estimation, testing, and modication. This basic understanding provides the framework for understanding the material presented in chapters 5 through 8 on model-t indices, regression analysis, path analysis, and conrmatory factor analysis models (measurement models), which form the basis for understanding the structural equation models (latent variable models) presented in chapters 9 and 10. Chapter 11 provides guidance on reporting structural equation modeling research. Chapter 12 addresses techniques used to establish model validity and generalization of ndings. Chapters 13 to 16 present many of the advanced SEM models currently appearing in journal articles: multiple group, multiple indicators-multiple causes, mixture, multilevel, structured means, multitrait-multimethod, second-order factor, dynamic factor, interaction
models, latent growth curve models, and Monte Carlo studies. Chapter 17 presents matrix notation for one of our SEM applications, covers the different matrices used in structural equation modeling, and presents multiple regression and path analysis solutions using matrix algebra. We include an introduction to matrix operations in the Appendix for readers who want a more mathematical understanding of matrix operations. To start our journey of understanding, we rst ask, What is structural equation modeling? Then, we give a brief history of SEM, discuss the importance of SEM, and note the availability of SEM software programs.