Best of #econtwitter - Week of December 18, 2022: paper summaries
Welcome readers old and new to this week’s edition of Best of Econtwitter. Please submit suggestions — very much including your own work! — over email or on Twitter @just_economics.
A slightly different format this week (also, gmail may cut off the email, and you would need to open in the browser to see all tweets). Feedback, as always, is welcome.
^interesting application, but also important conceptual point about interpreting these kinds of conditional means more generally:
^i.e.: “who is a HS dropout in 1965” is not the same as “who is a HS dropout in 2015”, and this makes a LOT of graphs you see on the internet useless. They develop a nice partial identification methodology for addressing these selection issues
^early death instrument
Metrics pop-up section
On transforming your dependent variable: