I'm running an event study using the well-cited Princeton example (https://dss.princeton.edu/online_help/stats_packages/stata/eventstudy.html), but I'm confused about the timing of their event window.

If an event takes place at t=0, why is the event window set up between -2 and 2? My intuition is that this would underestimate the effect of the event because they capture part of the 'untreated' series. Could anyone tell me why they do this and whether I'm making an error by starting my event window at t=0?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.