The videos provide some background for our synchronous discussion of structural equation modeling (SEM). A discussion of covariance, since covariance matrices are used for structural equation modeling and covariance may be unfamiliar to some participants. The other video provides another tie-in with covariance matrices and highlights some key research questions that can be addressed through the use of structural equation modeling. The synchronous discussion will examine published research studies related to a subset of the questions raised in Video 2.
Video 1: SEM covariance (Time: 6:45)
This video discusses the difference between variance and covariance, covariance and correlation, and how covariance is calculated.
Video 2: SEM Research Questions (Time: 14:14)
This video discusses the structure of a covariance matrix. Subsequently, the video goes into different kinds of research questions that a researcher may have that can be addressed through the use of structural equation modeling. The video ends with a brief outline of some of the advantages of structural equation modeling over techniques like multiple regression.
Be sure to check out the SEM Resources document. In addition to references related to SEM, there is information about a FREE 3-day SEM course. As a bonus, there is also information about a FREE workshop on meta-analysis.
During the synchronous portion of this seminar, we will discuss examples from published research across a variety of subject areas, different foci for the research questions, and interpreting results.
Video 1: SEM covariance
Video 2: SEM Research Questions
Byrne, B. M. (1998). Structural equation modeling with LISREL, PRELIS, and SIMPLIS: Basic concepts, applications and programming. Mahwah, NJ: Lawrence Erlbaum Associates, Publishers.
Collier, J. E. (2020). Applied structural equation modeling using AMOS: Basic to advanced techniques. New York: Routledge.
Marcoulides, G. A., & Schumacker, R. E. (1996). Advanced structural equation modeling: Issues and techniques. Mahwah, NJ: Lawrence Erlbaum Associates.
Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Mahwah, NJ: Lawrence Erlbaum Associates, Publishers.
The Center for Statistical Training by Curran-Bauer Analytics (centerstat.org)
FREE(!) Three-day livestreamed Introduction to Structural Equation Modeling webinar
Register at https://centerstat.org
May 10 – May 12: Dan Bauer & Patrick Curran
This workshop is broadly targeted towards research applications in behavioral, health, educational and psychological sciences, although the methods apply to many other disciplines as well. We recommend that participants have a working knowledge of the general regression model. Those who need a refresher may wish to check out episodes on our linear regression playlist on YouTube.
Live software demonstrations will be provided in R at the end of each day and pre-recorded demonstrations in Stata and Mplus will be posted each day. Note that R can be downloaded for free. While it is helpful to have some familiarity with R, this is not necessary. The lectures which constitute the majority of the workshop are software-independent.
Rochelle S. Michel has held a number of roles in the context of educational testing, assessment, educational research, and non-profit program management, including working as the Executive Director of Admission Programs at Educational Records Bureau, Director of Research within the Academic to Career Research Center at Educational Testing Service (ETS),
Research Director at Curriculum Associates, and Psychometric Manager at ETS. She served as the president of the Northeastern Educational Research Association in 2018-2019. She also has extensive teaching experience in Mathematics and Statistics, at the junior high school, high school, and college levels. Dr. Michel received her PhD in Psychometrics from Fordham University and currently is a Lecturer in the Masters of Science and Social Policy program at the University of Pennsylvania. Dr. Michel is an Institute Fellow of the
Institute in Critical Quantitative, Computational, and Mixed Methodologies.