Resources
Textbooks
These textbooks provide a number of the readings that will be used through the course of the semester. Each is available either as a free online version or in digital form via UW-Madison library access.
- Gelman, Andrew, Jennifer Hill, and Aki Vehtari. Regression and Other Stories. Cambridge University Press, 2020.
- Gelman, Andrew, John Carlin, Hal Stern, David Dunson, Aki Vehtari, and Donald Rubin. Bayesian Data Analysis. 3rd Edition. Chapman and Hall/CRC, 2013.
- James, Gareth, Daniela Witten, Trevor Hastie, and Robert Tibshirani. An Introduction to Statistical Learning. Springer, 2013.
- Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd Edition. Springer, 2009.
- McElreath, Richard. Statistical Rethinking: A Bayesian Course with Examples in R and Stan. 2nd Edition. Chapman and Hall/CRC, 2020.
- Aronow, P. M., and Benjamin T. Miller. Foundations of Agnostic Statistics. Cambridge University Press, 2019.
- Evans, Michael J., and Jeffrey S. Rosenthal. Probability and Statistics: The Science of Uncertainty. 2nd Edition. W.H. Freeman, 2010.
- Rasmussen, Carl Edward, and Christopher K. I. Williams. Gaussian Processes for Machine Learning. MIT Press, 2006.
Software
R and RStudio
This course uses R for all programming assignments. You are welcome to use the RStudio Interactive Development Environment (IDE) to write code and edit the assignment write-up. Due to the extensive integration of Quarto into Posit-developed IDEs, I encourage using either RStudio or the more recent Positron IDE.
- R: Download from https://www.r-project.org
- RStudio: Download from https://posit.co/download/rstudio-desktop/
- Positron: Download from https://positron.posit.co/
Recommended Guides for R Programming
- R For Data Science Available at https://r4ds.hadley.nz/
- Data Visualization: A Practical Introduction Available at https://socviz.co/
Stan
We will use Stan for specifying and estimating Bayesian models. Stan is written in C++ but has bindings for a variety of programming languages. In this course we will use two interfaces to Stan from R: RStan and brms. Running Stan locally requires a working C++ toolchain – consult the installation guide for the specific requirements of your operating system.
- Installation guide: https://mc-stan.org/install/
- Stan user’s guide: https://mc-stan.org/docs/stan-users-guide/
- brms: https://paulbuerkner.com/brms/
Quarto and Markdown
The assignments are distributed as .qmd Quarto files. Quarto is the successor to R Markdown and lets you present your analysis, code, figures and written discussion all in a single document. It uses Markdown syntax for formatting text and supports embedded R code chunks that execute when you render the document.
To complete assignments, you will edit the provided .qmd file, adding your code and written responses, then render it to an HTML file for submission. Both your .html output and .qmd file will be submitted via Gradescope.
- Quarto: Download from https://quarto.org/docs/get-started/
- Quarto Guide: https://quarto.org/docs/guide/
- Markdown Basics: https://quarto.org/docs/authoring/markdown-basics.html
- Note also the chapter on Quarto in R For Data Science