Caitlin and I are again after a one week hiatus as we every ran round touring in our respective elements of the world. In all probability for the most effective, because it allowed two weeks of twoway fastened results decompositions to marinate. However now it’s time — can we lastly see what a steady remedy difference-in-differences estimator truly is for goodness sake? And the reply is form of!
On this episode, me and Caitlin wrap up a stroll by way of of what parameters we’re figuring out with our abortion-marriage paper. I used to be actually puzzled to be trustworthy within the final episode as to what a “dose” even meant in our context. As you might recall, we’re finding out the impact of Home Invoice 2 which brought about half of Texas’s abortion clinics to shut, and in flip made the space to the closest abortion clinic to rise. However that led us to surprise:
1. Are we finding out the impact of distance to the closest clinic after Home Invoice 2, or
2. Are we finding out the impact of the change in distance to the closest clinic after Home Invoice 2?
So, have enjoyable as you take heed to us speak by way of it out and eventually understand on the finish that it might seem our dose have to be a type of and can’t be the opposite because of the nature of the design and diff-in-diff itself. Trace: no anticipation locations some rails on us. See in the event you can work out why.
However then we additionally dive into the continual remedy diff-in-diff estimator. You’ll find out about splines! You’ll find out about kernels! You’ll find out about polynomials! You’ll find out about b-splines and wavelets and a bunch of different issues that draw curvy traces! And also you’ll be taught concerning the one state of affairs when you have got the permission to interpret that line as a causal impact too!
Thanks once more for all of your help! We hope you get pleasure from this episode!
