Dear all,
I am trying to estimate a staggered diff-in-diff.
I have a panel dataset of schools and years. I am currently using the jwdid estimator, as it allows for interaction terms. My goal is to estimate a heterogeneous treatment effect based on the rating of schools at t-1. The rating is given by a series of dummies d_lrat3 d_lrat4 d_lrat5
If I read the output correctly (the output is quite long so I have attached in a txt file), in theory the jwdid command should be able to estimate this. However, I am unsure on how to plot the relevant treatment effect for (for example) d_lrat3. I think that estat event only plots the ATT, discarding the heterogeneity by rating.
Is it possible to plot the ATT for d_lrat3==1?
Thank you very much in advance and please let me know if you need more information.
Ludovica
I am trying to estimate a staggered diff-in-diff.
I have a panel dataset of schools and years. I am currently using the jwdid estimator, as it allows for interaction terms. My goal is to estimate a heterogeneous treatment effect based on the rating of schools at t-1. The rating is given by a series of dummies d_lrat3 d_lrat4 d_lrat5
If I read the output correctly (the output is quite long so I have attached in a txt file), in theory the jwdid command should be able to estimate this. However, I am unsure on how to plot the relevant treatment effect for (for example) d_lrat3. I think that estat event only plots the ATT, discarding the heterogeneity by rating.
Is it possible to plot the ATT for d_lrat3==1?
Thank you very much in advance and please let me know if you need more information.
Ludovica
Code:
** pc is the school id xtset pc year jwdid log_grades d_lrat3 , ivar(pc) tvar(year) gvar(year_of_treat) never corr estat event, window (-6 7)
Comment