Ideal for researchers and graduate students in the social sciences who require knowledge of structural equation modeling techniques to answer substantive research questions, Using Mplus for Structural Equation Modeling provides a reader-friendly introduction to the major types of structural equation models implemented in the Mplus framework. This practical book, which updates author E. Kevin Kelloway’s 1998 book Using LISREL for Structural Equation Modeling, retains the successful five-step process employed in the earlier book, with a thorough update for use in the Mplus environment. Kelloway provides an overview of structural equation modeling techniques in Mplus, including the estimation of confirmatory factor analysis and observed variable path analysis. He also covers multilevel modeling for hypothesis testing in real life settings and offers an introduction to the extended capabilities of Mplus, such as exploratory structural equation modeling and estimation and testing of mediated relationships. A sample application with the source code, printout, and results is presented for each type of analysis.
Multilevel (also known as hierarchical linear or mixed) models are becoming increasingly prevalent in social science research. The popularity of the technique arises from the recognition that our data often exist in clusters: We study students (who are clustered in classrooms), employees (who are clustered in teams or work groups), or customers (who are clustered in service units). This clustering has some serious consequences for the analytic techniques we use and can have some unexpected effects on our analysis.
Most of our analytic techniques (e.g., regression, analysis of variance) assume that the observations are independent. Obviously, if our data exist in a clustered or nested structure, we are violating the assumption of independence. For example, in a study of leadership, we might have ...