MAKING BETTER DECISIONS IN CAUSAL ANALYSIS: AN INTRODUCTION TO STRUCTURAL EQUATION MODELING WITH LATENT VARIABLES.

Background: This short course will make Structural Equation Modeling (SEM) accessible to a wide audience of researchers across many disciplines. SEM is a very general and powerful technique to link conceptual models, path diagrams, factor analysis and other mathematical models. These techniques allow for 1) the combination of continuous, categorical and latent and observed variables; 2) modeling of causal relationships including multiple direct and indirect effects in a single analysis; 3) cutting-edge techniques for model selection and comparison; 4) compact representation of cost-utility problems; 5) dynamic updates to model predictions as new clinical measures are obtained; and 6) the ability to break down complex causal structures into many smaller, more manageable local models which can then be combined together. These advantages are particularly applicable to both theoretical and applied research problems in medical decision making.

Format Requirements: Participants will experience a mixture of lecture and discussion. We will introduce basic concepts and vocabulary of SEM and Bayesian networks (BN), give real-world examples and conduct sample analyses using SEM software. No prior knowledge of SEM or BN is required. Participants with a basic understanding of statistics will benefit most from this course.

Description and Objectives:

We present a basic overview of SEM and BN principles, some common nomenclature, diagrams, a tiny bit of algebra (with few Greek letters!), real world examples, and a glimpse into more advanced SEM techniques such as measurement invariance testing, latent growth curve modeling and how Bayesian networks are related to SEM. In this course, you will:

• Enrich your way of thinking about certain medical decision making problems;
• Learn fundamental concepts underpinning SEM and BN models;
• Gain knowledge of resources and techniques for causal modeling;
• Be introduced to software for implementing SEM and BN analyses;
• Be able to interpret results of advanced causal modeling techniques;
• Understand advantages of SEMs and BNs over traditional statistical models.

Whether you want to know how to critique a SEM or BN article, or want to engage a few SEM researchers in some feisty methods discussions, sign up for this course...we'd love to visit with you.