Open Mbjoerkh opened 4 years ago
I apologize if this is an obvious question, but would really appreciate if someone has a chance to answer /make a suggestion (I'm new to R, so what is obvious to others might not be to me).
@Mbjoerkh This seems like more of a theoretical issue than a technical one. It seems OK to estimate the effect in each state by restricting analyses to those states. Whether you could then combine the effect estimates together might require additional assumptions of transportability or generalizeability of effects. As you may know, there is some literature on this, e.g., here: https://academic.oup.com/aje/article-abstract/188/2/438/5123986
Hi,
I want to limit donor pool to untreated firms in the same state. Is there a way to do this, beside running the code separately for each state and combine results at the end? Beside being tedious, combining the results would present some challenges.
Thanks, Markus