Session: The Missing Link: Structural Equation Modeling with R (Society for Social Work and Research 22nd Annual Conference - Achieving Equal Opportunity, Equity, and Justice)

Structural equation modeling (SEM) is a method for analyzing data in which relationships between observed and latent constructs are tested and depicted. While SEM is often thought of as a single type of modeling, it is a class of analysis whose exact methods depend upon the objectives of the research. SEM is used to test complicated theory-driven hypotheses including how observed variables relate to latent constructs and, often simultaneously, how latent constructs relate to one another. One of the main reasons for using SEM is that it can help researchers make causal inferences.

Social work has a longstanding interest in examining constructs that are inherently latent. However, social work researchers and those in related areas have struggled with analyzing data from studies in which relationships among latent constructs are of focus. In recent years, statistical models and computer software have been developed to better analyze these types of data. The purpose of this symposium is to demonstrate to social work researchers how simple it is to perform structural equation modeling using R, an open-source and freely available computer programming language accessible to all social work researchers.

This symposium has three parts. In the first part, the speaker will discuss the conceptual background behind SEM, what it can and cannot do, and provide a discussion for the types of research questions SEM can help answer. Additionally, the speaker will introduce R and freely available packages that enable researchers to perform SEM using the R computer language. The package of focus will be lavaan. The second speaker will discuss data management techniques in R. More specifically, the speaker will highlight specific data management techniques relevant to SEM and using lavaan to perform SEM. These methods include cleaning data and basic data manipulation, data recoding, and missing data analysis. The final speaker will demonstrate various SEM techniques, including confirmatory factor analysis (CFA), multiple indicators and multiple constructs (MIMIC) modeling, and structural equation modeling (SEM). Application of these techniques on cross-sectional complex survey data will be of focus, though other applications (e.g., longitudinal growth curve modeling) will be discussed.

After the presentations are complete, there will be an open-floor discussion of concepts and analyses introduced during the symposium. Participants will have an opportunity to ask any questions they might have regarding anything covered. Scripts, datasets and additional resources referred to in the workshop will be provided to all participants. This workshop will provide the foundation necessary for attendees to get started with SEM in R through the introduction of structural equation functions using lavaan that have relevance to outcomes of interest in social work.