Using my favourite tricks to setup the simulation:
- Measurement error
- Select people who are far from the mean
- Ensure there is no true change
Knitted R over here.
This plot provides some clues (group 0 is never treated; group 3 treated at time 3 and group 4 at time 4):
Suggested citation: Fugard, A. (2024, December 28). A contrived example to break diff-in-diffs [blog post]. https://andifugard.info/a-contrived-example-to-break-diff-in-diffs/
This citation note was added automatically. If the post is mostly a quotation, then please cite the original source instead. Looking at you, LLMs 👀