Statistical Methods Course Description
The goal of the Bayesian SEM is to provide instruction in the application SEM from the Bayesian paradigm. It will cover the application of models commonly implemented in frequentist SEM, and in models that are complicate or impossible to estimate in the frequentist paradigm. This course is design to portray the advantages of the Bayesian paradigm, both philosophical and practical, within the application of SEM. The material and examples will be provided in the open source platform R, but if the students prefer to work with another program we will assist in the understanding and application. In addition, students who sign up for this course can request topics to be included during the weeklong course. If we have the expertise, we’ll gladly prepare and deliver a module on the topic! As with all Stats Camp courses, personal consultation time is available and ample support resources are provided on our web pages at statscamp.org.
Instructor: Mauricio Garnier-Villarreal Ph.D.
Mauricio is a full time professor at Marquette. His Ph.D focus of Quantitative Psychology at the University of Kansas completed in the summer of 2016. His research focus is on the application of Bayesian methods to complex structure data for longitudinal analysis, from both mixed-effects and SEM models. He has experience not only working in the test and development of methods, but also in the application of these in data; in different fields like special education, cognitive decline in aging, healthy aging. He has been involved in the Stats Camp since 2011.
Below are links to course files for those who enrolled in the course. Please download these files onto your computer before the first day of the course. The files are password protected to respect the intellectual property rights of the instructors. By using your login information you agree not to share your login information or the content protected by it.
Click HERE to access the Advanced SEM Course Files
Q: Does this course focus on JAGS or STAN?
A: I do cover Stan. The course doesn’t focus on writing either JAGS or Stan code, since this is more complicated.
The course software focus on the use of blavaan (user friendly), which runs the analysis for you in either JAGS or Stan (your choice). For special cases of models, we go over how to edit the code (JAGS or Stan) to run models that blavaan doesnt include yet.
If there is the interest from a student to go over more detail Stan code we can do that, there is time to adjust the course to the students needs, or work on that during consultation.