Tenth Summer School on Statistical Methods for Linguistics and Psychology

Advanced methods in frequentist statistics with Julia

Authors

Phillip Alday

Reinhold Kliegl

Published

2026-04-10

This site provides materials for the Advanced frequentist methods stream of the Summer School on Statistical Methods to be held at the University of Potsdam, 24–28 August 2026.

1 Installation of tools prior to the course

This section of the summer school will use the Julia programming language and related tools. Because most students in the course will have more experience with R and the RStudio integrated development environment (IDE), it is necessary to install and configure several software systems prior to the course.

1.1 git

We will assume that you have git installed and are able to clone a repository from github. If not, Happy Git with R is a good place to learn about git for data science.

The example data stored in the data folder is stored with git-lfs. You will need to install git-lfs to access this data, but then everything will “just” work.

This website is built using quarto, described below, from the repository. Clone this repository with, e.g.

git clone https://github.com/RePsychLing/SMLP2026

1.2 Julia Programming Language

We will use the latest stable release of Julia. We recommend using Juliaup to install and manage Julia versions. Juliaup makes it trivial to upgrade to new Julia releases or even use old ones. Alternatively, you can download the version appropriate for your setup from here: Julia Programming Language

There are resources available online for new Julia users and several specialize in Julia for R users:

1.3 Quarto

The web site and other documents for this course are rendered using a knitr-like system called Quarto. You can download the version appropriate for your setup from here: quarto

1.3.1 Command line

From the root of the cloned repository, two commands cover most workflows:

quarto preview

quarto preview renders the site and opens it in a browser, then watches for changes and re-renders automatically. It is the most convenient way to work on materials locally.

quarto render

quarto render renders the entire site once to the _build/ output directory. Use this to do a clean full build, e.g. before checking the final output.

Both commands accept a single file as an argument to work on just that document:

quarto preview lmm-intro/sleepstudy.qmd
quarto render lmm-intro/sleepstudy.qmd

1.3.2 VS Code Quarto extension

Install the Quarto extension for VS Code (quarto.quarto) from the Extensions panel. It provides:

Preview (Ctrl+Shift+K / Cmd+Shift+K): renders the current .qmd file and shows a live preview in a side panel, updating on save.
Render (Ctrl+Shift+P → Quarto: Render): renders the current file to its output format.
Render Project (Ctrl+Shift+P → Quarto: Render Project): equivalent to quarto render from the command line.
Syntax highlighting, code completion, and cell execution for Julia code chunks directly in the editor.

1.4 Integrated Development Environment (IDE)

An integrated development environment (IDE) makes editing and running Julia and Quarto source files easier. The “integrated development” portion is a clue to what makes them different than a text editor (even a text editor with syntax highlighting): they have tools for suggesting code completion, interacting with and running code and much more. Popular ones for R and Python include RStudio and Spyder. For Julia, we recommend VS Code or Positron. VS Code is widely used in the Julia community, while Positron is a new fork of VS Code aimed at data scientists and developed by the Posit, the folks behind RStudio and Quarto.

Whatever IDE you use, make sure to install the necessary extensions for Quarto and Julia.

2 Summary

We assume everybody will succeed with the installations. If not, please get in touch!

You may also want to give it a try to get these tools to play nicely with each other – but don’t spend too much time on this.

This page was rendered from git revision 0e399c4 using Quarto 1.9.36.