search

synth-inference / synthdid

Synthetic difference in differences
https://synth-inference.github.io/synthdid
BSD 3-Clause "New" or "Revised" License
262 stars 97 forks source link

Staggered adoption #73

Open SiqiQAQ opened 2 years ago

SiqiQAQ commented 2 years ago

Hi! Thanks for this useful package! I have some difficulties in estimating tau_hat and se for staggered adoption case. I read Athey S, Imbens G W. Design-based analysis in difference-in-differences settings with staggered adoption[J]. Journal of Econometrics, 2021. The authors suggest that researchers can get weighted average estimator for subsamples of each adoption period. But I didn't figure out how to implement that in R. (I am a total beginner in R and also new to Github) Do you have any suggestions? Thanks!

zachporreca commented 2 years ago

I have written a code to accomplish this (based on the appendix to the paper). It is still in an early form, with issues listed in the readme. You can have a look here staggered_adoption_synthdid

SiqiQAQ commented 2 years ago

I have written a code to accomplish this (based on the appendix to the paper). It is still in an early form, with issues listed in the readme. You can have a look here staggered_adoption_synthdid

Thank you! I will look into that!

TJhon commented 1 year ago

I just wrote a code for this case based on the Stata code for staggered treatment periods, also rewrote vcov for those cases, and simplified the way to implement covariates in the model. You can view the code here ssynthdid.

zachporreca commented 1 year ago

Awesome, thanks TJhon! I just linked to your code on the page for mine. Since, it seems the objective is now handled by more capable hands I will no longer maintain my code and will leave it up to you.

SiqiQAQ commented 1 year ago

Thank you so much for your work!

Siqi Yang 思琪杨 Ph.D. Candidate Department of Economics, UVa E-mail: @.***

On Apr 29, 2023, at 15:18, Jhon Flores Rojas @.***> wrote:

I just wrote a code for this case based on the Stata code for staggered treatment periods, also rewrote vcov for those cases, and simplified the way to implement covariates in the model. You can view the code here ssynthdid. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>