Applied Bayesian Data Analysis - Online Course
A 3-Day Livestream Seminar Taught by
Roy LevyThursday, January 21 —
Saturday, January 23, 2027
10:00am-12:30pm (convert to your local time)
1:30pm-3:30pm
Bayesian methods have revolutionized statistics over the last quarter of a century. This is not an exaggeration. The appeal of Bayesian statistics lies in its intuitive basis for making direct probability statements and its ability to blend disparate types of data into the same model.
Bayesian models take existing knowledge and update it as new data becomes available, a principle that works across all scientific disciplines. The cost of this added inferential power is more reliance on computing. Fortunately, there are powerful software packages for Bayesian statistics that are free and easy to use (with some training).
This seminar assumes no prior experience with Bayesian statistical modeling and is intended as both a theoretical and practical introduction. An understanding of Bayesian statistical modeling will be developed by relating it to your existing knowledge of traditional frequentist approaches. The philosophical underpinnings and departures from conventional frequentist interpretations of probability will be explained. This, in turn, will motivate the development of Bayesian statistical modeling.
Starting January 21, this seminar will be presented as a 3-day synchronous, livestream workshop via Zoom. Each day will feature two lecture sessions with hands-on exercises, separated by a 1-hour break. Live attendance is recommended for the best experience. If you can’t join in real time, recordings will be available within 24 hours and accessible for four weeks after the seminar.
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.
ECTS Equivalent Points: 1
NOTE: This course is designed for those who have no previous experience with Bayesian methods. If you are looking to learn more advanced methods, check out Applied Bayesian Data Analysis: A Second Course.
More details about the course content
To introduce Bayesian principles in familiar contexts, we will begin with simple binomial and univariate normal models, and then move to simple regression and multiple regression. Along the way, we will cover several aspects of modeling, including model construction, specification of prior distributions, graphical representations of models, practical aspects of Markov chain Monte Carlo (MCMC) estimation, hypothesis evaluation, data-model fit, and model comparison
Although Bayesian statistical modeling has proven advantageous in many disciplines, we’ll use examples that are drawn primarily from social science and educational research. Examples will be accompanied by input and output from the free software R, using several R packages. There will be exercises for you to do using these packages.
To introduce Bayesian principles in familiar contexts, we will begin with simple binomial and univariate normal models, and then move to simple regression and multiple regression. Along the way, we will cover several aspects of modeling, including model construction, specification of prior distributions, graphical representations of models, practical aspects of Markov chain Monte Carlo (MCMC) estimation, hypothesis evaluation, data-model fit, and model comparison
Although Bayesian statistical modeling has proven advantageous in many disciplines, we’ll use examples that are drawn primarily from social science and educational research. Examples will be accompanied by input and output from the free software R, using several R packages. There will be exercises for you to do using these packages.
Computing
Examples will be accompanied by input and output from freely available software. Specifically, we will be using the R software package to conduct analyses and will interface with the Stan software for fitting models.
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.
We will not cover every possible command or option in R; instead we will focus on code and commands to execute the key functions to specify models and conduct analyses. You will be able to practice analyses using these packages.
For those who work with Mplus, code for conducting several of the examples in Mplus will also be provided, but will not be discussed in the seminar.
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.
Examples will be accompanied by input and output from freely available software. Specifically, we will be using the R software package to conduct analyses and will interface with the Stan software for fitting models.
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.
We will not cover every possible command or option in R; instead we will focus on code and commands to execute the key functions to specify models and conduct analyses. You will be able to practice analyses using these packages.
For those who work with Mplus, code for conducting several of the examples in Mplus will also be provided, but will not be discussed in the seminar.
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?
You should have a foundational knowledge of conventional frequentist approaches to statistics (e.g., hypothesis testing, confidence intervals, least-squares and likelihood estimation) in contexts up through multiple regression.
Although not required, your experience in this seminar will be enhanced by additional prior training or experience with more advanced statistical modeling techniques (e.g., general linear modeling, multivariate models for multiple outcomes) and/or by familiarity with the basics of probability theory (e.g., joint, marginal, and conditional distributions, independence).
You should have a foundational knowledge of conventional frequentist approaches to statistics (e.g., hypothesis testing, confidence intervals, least-squares and likelihood estimation) in contexts up through multiple regression.
Although not required, your experience in this seminar will be enhanced by additional prior training or experience with more advanced statistical modeling techniques (e.g., general linear modeling, multivariate models for multiple outcomes) and/or by familiarity with the basics of probability theory (e.g., joint, marginal, and conditional distributions, independence).
Seminar outline
Day 1
-
- Machinery and interpretations of probability
- Review of frequentist inference
- Introducing Bayesian inference
- Normal distribution models with unknown means
- Summarizing posterior distributions
- Accumulation of evidence
- Principles of specifying prior distributions
Day 2
-
- Normal distribution models
- Practical orientation to Markov chain Monte Carlo estimation
- Fitting models with software
Day 3
-
- Regression models
- Evaluating hypotheses about parameters and comparing models
- Posterior predictive model checking
- Incorporating substantive information: Regression example (time permitting)
- Alternative prior specifications for variance terms (time permitting)
- Bayesian updating: Regression example (time permitting)
- Summary and additional resources
Day 1
-
- Machinery and interpretations of probability
- Review of frequentist inference
- Introducing Bayesian inference
- Normal distribution models with unknown means
- Summarizing posterior distributions
- Accumulation of evidence
- Principles of specifying prior distributions
Day 2
-
- Normal distribution models
- Practical orientation to Markov chain Monte Carlo estimation
- Fitting models with software
Day 3
-
- Regression models
- Evaluating hypotheses about parameters and comparing models
- Posterior predictive model checking
- Incorporating substantive information: Regression example (time permitting)
- Alternative prior specifications for variance terms (time permitting)
- Bayesian updating: Regression example (time permitting)
- Summary and additional resources
Payment information
The fee of $995 USD includes all course materials.
PayPal and all major credit cards are accepted.
Need funding from your employer or institution? Use our funding request template.
Our Tax ID number is 26-4576270.
The fee of $995 USD includes all course materials.
PayPal and all major credit cards are accepted.
Need funding from your employer or institution? Use our funding request template.
Our Tax ID number is 26-4576270.