A research-level course in applied Bayesian data analysis for readers who know basic probability, linear regression and some R. Every model starts from a causal graph and a simulated prior, is fitted in R with brms and Stan, checked, and written up to a publishable standard, on modern real data from public health, genomics, sport, education and AI.

Start reading 33 lectures in 14 chapters, plus an afterword

Contents

1. Chapter 1The Causal–Bayesian Workflow
2. Chapter 2Choosing Causal Graphs and Priors
3. Chapter 3Bayesian Linear Models
4. Chapter 4Generalized Linear Models
5. Chapter 5Markov Chain Monte Carlo
6. Chapter 6Multilevel Models
7. Chapter 7Missing Data
8. Chapter 8Time-Dependent Data
9. Chapter 9Variational Inference
10. Chapter 10Bayesian Machine Learning
11. Chapter 11Unsupervised Models: Factors, Mixtures and Copulas
12. Chapter 12Text and Image Data
13. Chapter 13Causal Inference in Depth
14. Chapter 14Bayesian Deep Learning and Causal AI
15. AfterwordThe Workflow, and What Comes Next