[Luca Toni]

Hi Luca,

Correct me if I am wrong: I think you want to estimate the impact after the end of the monitoring period!

If it is, you can once exclude three periods (period == 1,2,3) and then estimate the impact. Also, now that you have your period variable, you can think of a staggered DiD approach. Its benefit lies under the logic of control/treatment comparison, while in the RD you may not argue that your impact is causal since by dropping 3 periods you may lose the similarity near the cutoff. As another advantage of DiD, without even excluding those three periods, and only by referencing period 0 or -1 by plotting the coeffs you can see the impacts in all periods after the sanctions.

Thanks Ali.
I think staggered DiD might work here. If I use staggered DiD, then I can see as well if I get the same results from the RD estimation, without excluding the monitoring period.
Now, assuming I'm going with your advice of excluding the monitoring period and using a staggered DiD, my question is how I'm going to select the football clubs that will represent my control group, other than the fact that they were not sanctioned? I assume that I need to be careful here to avoid a selection bias. I also assume there is a way to match between the treatment and control group based on the market value of the club and the league, but I'm not familiar with such way.

[Ali Bahrami Sani]

Thanks Ali.
I think staggered DiD might work here. If I use staggered DiD, then I can see as well if I get the same results from the RD estimation, without excluding the monitoring period.
Now, assuming I'm going with your advice of excluding the monitoring period and using a staggered DiD, my question is how I'm going to select the football clubs that will represent my control group, other than the fact that they were not sanctioned? I assume that I need to be careful here to avoid a selection bias. I also assume there is a way to match between the treatment and control group based on the market value of the club and the league, but I'm not familiar with such way.

Matching requires enough variables to conduct it. Also, for defining treat/ctrl groups, if you have clubs that never sanctioned you can consider them as your ctrl group!

[Luca Toni]

Matching requires enough variables to conduct it. Also, for defining treat/ctrl groups, if you have clubs that never sanctioned you can consider them as your ctrl group!

Hi Ali,

I hope you are doing fine.
I collected data for my control group and I want to use staggered DiD, just like you suggested before (excluding periods 1,2,3). However, I'm not familiar with how I'm going to code it as it's not a standard DiD.
Could you please guide me in this case?

Thank you.