Upon successful completion of the course, students will be able to apply a variety of statistical techniques utilizing structural equation models (SEMs) to address specific research questions. Students will be able to recognize, evaluate and interpret various types of parameter estimates, and be able to judge the appropriateness of the use of SEMs presented in the scientific literature. Most importantly, students who successfully complete the course will be able to describe the theoretical underpinnings of structural equation models, report and interpret results of SEMs, and utilize these methods in their subsequent research. 

Structural equation modeling (SEM) consists of numerous analytic techniques that examine relationships between one or more independent variables (predictors) and one or more dependent variables (outcomes). This methodology may be applied to concurrent and longitudinal data from experimental and non-experimental studies, and has several advantages over other methods, including the ability to account for missing values and measurement error (through the use of latent constructs). Structural equations describe how observed variables and/or latent constructs are related to one another. Relations between predictors and outcomes describe the structural portion of the model, whereas relationships between latent constructs and how well they are represented by observed variables represent the measurement portion of the model. That is, regression and confirmatory factor analyses may be integrated into a structural equation model. Due to its flexibility, SEM is commonly used by behavioral and social scientists. Theoretical issues involving SEM such as model identification and measurement invariance are discussed; as are commonly used techniques such as path models, cross-lagged panel models, and latent growth curve models.
Teaching methods: lectures and computer-laboratory.