Great article! I have in my ideas queue a write-up on why synthetic controls are not a good approach. (The N=1 problem is a major issue which is why it appears synthetic controls have very large effect estimates compared to more traditional methods).
Great article! I have in my ideas queue a write-up on why synthetic controls are not a good approach. (The N=1 problem is a major issue which is why it appears synthetic controls have very large effect estimates compared to more traditional methods).