Applied Bayesian Data Analysis: A Second Course - Online Course
A 3-Day Livestream Seminar Taught by
Roy LevyThursday, December 5 –
Saturday, December 7, 2024
10:00am-12:30pm (convert to your local time)
1:30pm-3:30pm
NOTE: this course is designed for those who have previous experience with Bayesian methods. If you are looking to learn Bayesian analysis basics, check out Applied Bayesian Data Analysis.
Bayesian approaches to data analysis offer a number of advantages over conventional approaches. In addition, several advanced methods and models may be seen as implicitly or explicitly Bayesian. This seminar describes Bayesian approaches, and their attending advantages, in several advanced modeling frameworks, including factor analysis, structural equation models, and multilevel models.
Building off an understanding of Bayesian normal distribution and regression modeling, this seminar will cover Bayesian confirmatory factor analysis in depth, including procedures for model evaluation and model comparison. Importantly, we will cover the components of factor analysis in detail because they will also serve as the components for the other advanced models we will cover, including structural equation modeling, multilevel modeling, and (time permitting) missing data modeling. The presentation of each of these topics is intended to illuminate broader ideas of Bayesian statistical modeling, such that key principles can be abstracted even for those researchers not working with the particular type of model at hand.
Starting December 5, we are offering this seminar as a 3-day synchronous*, livestream workshop held via the free video-conferencing software Zoom. Each day will consist of two lecture sessions which include hands-on exercises, separated by a 1-hour break. You are encouraged to join the lecture live, but will have the opportunity to view the recorded session later in the day if you are unable to attend at the scheduled time.
*We understand that finding time to participate in livestream courses can be difficult. If you prefer, you may take all or part of the course asynchronously. The video recordings will be made available within 24 hours of each session and will be accessible for four weeks after the seminar, meaning that you will get all of the class content and discussions even if you cannot participate synchronously.
Closed captioning is available for all live and recorded sessions. Captions can be translated to a variety of languages including Spanish, Korean, and Italian. For more information, click here.
More details about the course content
Familiarity with conventional approaches to factor analysis, structural equation models, multilevel models, and missing data models would be beneficial, but not required. Each will be reviewed from a conventional perspective before pursuing a Bayesian perspective. Although this material is necessarily complex, it will be presented in a manner targeting the applied researcher, with examples primarily from social science and educational research, accompanied by input and output from software. Examples will be accompanied by input and output from Stan and R. Throughout the course you will be able to practice exercises using these software packages.
By the end of this seminar, you will be able to:
-
- Understand Bayesian approaches to inference and analysis.
- Construct Bayesian latent variable and multilevel models.
- Specify prior distributions for parameters of those models, including measurement model parameters, structural parameters, means, and covariance structures.
- Fit a variety of factor analytic, structural equation modeling, and multilevel models using Bayesian approaches.
- Interpret output from Markov chain Monte Carlo (MCMC) estimation, and diagnose warning signs of problems with model estimation.
- Evaluate hypotheses about models, parameters, and examine model-data fit.
Familiarity with conventional approaches to factor analysis, structural equation models, multilevel models, and missing data models would be beneficial, but not required. Each will be reviewed from a conventional perspective before pursuing a Bayesian perspective. Although this material is necessarily complex, it will be presented in a manner targeting the applied researcher, with examples primarily from social science and educational research, accompanied by input and output from software. Examples will be accompanied by input and output from Stan and R. Throughout the course you will be able to practice exercises using these software packages.
By the end of this seminar, you will be able to:
-
- Understand Bayesian approaches to inference and analysis.
- Construct Bayesian latent variable and multilevel models.
- Specify prior distributions for parameters of those models, including measurement model parameters, structural parameters, means, and covariance structures.
- Fit a variety of factor analytic, structural equation modeling, and multilevel models using Bayesian approaches.
- Interpret output from Markov chain Monte Carlo (MCMC) estimation, and diagnose warning signs of problems with model estimation.
- Evaluate hypotheses about models, parameters, and examine model-data fit.
Computing
Models and exercises for this seminar will be conducted using R and Stan, through multiple R packages for interfacing with Stan and processing output. You will be instructed on how to download (free) versions of the software prior to the course, and will be given access to datasets and code for the examples. Code for other software platforms (including Mplus, JAGS, and BUGS) will also be included for several of the examples, but will not be the focus of instruction.
Basic familiarity with R is highly desirable, but even novice R coders should be able to follow the presentation and do the exercises. No previous experience with Stan is required, or expected.
If you’d like to take this course but are concerned that you don’t know enough R, there are excellent online resources for learning the basics. Here are our recommendations.
Models and exercises for this seminar will be conducted using R and Stan, through multiple R packages for interfacing with Stan and processing output. You will be instructed on how to download (free) versions of the software prior to the course, and will be given access to datasets and code for the examples. Code for other software platforms (including Mplus, JAGS, and BUGS) will also be included for several of the examples, but will not be the focus of instruction.
Basic familiarity with R is highly desirable, but even novice R coders should be able to follow the presentation and do the exercises. No previous experience with Stan is required, or expected.
If you’d like to take this course but are concerned that you don’t know enough R, there are excellent online resources for learning the basics. Here are our recommendations.
Who should register?
Graduate students, emerging researchers, and continuing researchers will benefit from this seminar. This seminar assumes experience with introductory level Bayesian statistical modeling, such that is provided in the introductory Applied Bayesian Data Analysis seminar, or from an analogous university course exposure elsewhere, or from individual study that covers such topics.
You should be familiar with foundational concepts of Bayesian inference (e.g., Bayes’ theorem, prior, likelihood, posterior) and practices (e.g., fitting models via software using Markov chain Monte Carlo simulation). You should also be familiar with Bayesian models for normally distributed data and linear regression. These will serve as the foundation for developing Bayesian approaches to the more advanced models.
Graduate students, emerging researchers, and continuing researchers will benefit from this seminar. This seminar assumes experience with introductory level Bayesian statistical modeling, such that is provided in the introductory Applied Bayesian Data Analysis seminar, or from an analogous university course exposure elsewhere, or from individual study that covers such topics.
You should be familiar with foundational concepts of Bayesian inference (e.g., Bayes’ theorem, prior, likelihood, posterior) and practices (e.g., fitting models via software using Markov chain Monte Carlo simulation). You should also be familiar with Bayesian models for normally distributed data and linear regression. These will serve as the foundation for developing Bayesian approaches to the more advanced models.
Seminar outline
Day 1
-
- Review of foundational Bayesian inference including regression
- Factor analysis (single and multiple factor models)
Day 2
-
- Model evaluation
- Structural equation modeling
- Multilevel modeling
Day 3
-
- Multilevel modeling
- Missing data (time permitting)
- Bayesian updating: regression example (time permitting)
- Summary & additional resources
Day 1
-
- Review of foundational Bayesian inference including regression
- Factor analysis (single and multiple factor models)
Day 2
-
- Model evaluation
- Structural equation modeling
- Multilevel modeling
Day 3
-
- Multilevel modeling
- Missing data (time permitting)
- Bayesian updating: regression example (time permitting)
- Summary & additional resources
Payment information
The fee of $995 includes all course materials.
PayPal and all major credit cards are accepted.
Our Tax ID number is 26-4576270.
The fee of $995 includes all course materials.
PayPal and all major credit cards are accepted.
Our Tax ID number is 26-4576270.