Workshop 2 – Rosseel / Mayer

Multilevel Structural Equation Modeling with lavaan

Yves Rosseel and Axel Mayer

The aim of this workshop is to provide an introduction to the multilevel structural equation modeling (SEM) framework with lavaan. We focus on the application of this framework to analyze multilevel data (for example: student scores, where students are nested in schools). First, we will discuss the relationship between classic (single-level) regression, multilevel regression, and SEM. We will do this both from a theoretical point of view as well as from a software point of view. We will show how and under which conditions (classic, non-multilevel) SEM software can produce identical results as dedicated multilevel (or mixed modeling) software. Second, we will demonstrate how lavaan can be used to analyze multilevel data. We will start from a regression perspective, and gradually proceed from a simple regression analysis, to a two-level regression analysis, towards more complicated models, exploiting the full power of the multilevel SEM framework. Third, we will take a latent-variable (CFA) perspective, and give various examples of multilevel CFA, and multilevel SEM involving latent variables. Fourth, we will introduce moderation and mediation within the multilevel SEM framework and provide some examples. Along the way, we will discuss many practical issues including the role of centering, the treatment of missing and/or non-normal data, and how to deal with categorical data.