One day – social data science tools

Four parts of ninety minutes, with the toolchain in the foreground

This version of the one-day course keeps the tools in the foreground: the language, the IDE, the document format, the package layer, version control, and where a finished piece of work is archived. The case is the one used in every format of the course, a Multi100 reanalysis of a claim made by the original author (OA) of a paper about how the European Union is framed across its member states, and so is the exercise, in which you reproduce a result recorded by Multi100, write the estimand behind the claim, work a menu of defensible alternatives and preregister one of them before you run it. What changes is the balance. The toolchain has a whole part to itself, whereas the replication-focused day gives it eighteen minutes. The first session in R is part of the day itself, and the closing part takes the report you rendered and asks where it would be deposited, registered and versioned so that someone else could find and re-run it.

	What happens	Length
Before the day	Install R and an IDE, download the workspace, read the claim.	1 to 2 hours, once
Part 1 – Credibility and software	What a claim is for, the evidence on how often findings hold up, and five analysts whose disagreement could be diagnosed because every one of them shared runnable code; then you get running.	90 minutes
Part 2 – The toolchain	The map of the tools and each layer of it in turn, then a first session in R in your own workspace.	90 minutes
Part 3 – The claim and its reproduction	The paper, its estimand and its graph; then you reproduce the recorded result to the third decimal.	90 minutes
Part 4 – Exploration, preregistration and archiving	The menu, an exploratory dot on the class chart, one analysis preregistered before it runs, and where the finished work is archived.	90 minutes
After the day	Where to go next: Quarto, git and GitHub, and the rest of the curriculum.	as you like