csdid repeated time values within panel

[Luca Toni]

Hi,

I want to run staggered DiD, where I have a few treatment years. I figured out I should use the csdid command. However, when I run

csdid OverallBalanceDeficit MarketValue, ivar(team) time(Year) gvar(first_treat) method(ipw)

I get the error "repeated time values within panel".
My gvar variable is zero for all untreated football teams, and for the treated teams - each football team gets the year of the treatment (2013,2014,2015, etc).
I set up the gvar this way:

 egen first_treat=csgvar(treat), tvar(Year) ivar(team)

. replace first_treat=0 if TreatmentGroup==0

Why do I keep getting the error? gvar looks to be specified well.

Thanks.

[FernandoRios]

Hi
This is not due to GVAR but your ivar and tvar.
Try the following, what happens if you do
xtset team year

If it gives you an error, then ID why, fix it and then come back to CSDID

[Luca Toni]

Hi
This is not due to GVAR but your ivar and tvar.
Try the following, what happens if you do
xtset team year

If it gives you an error, then ID why, fix it and then come back to CSDID

Thank you. I found my problem. I had duplicates in my excel spredsheet.

Another concern regarding the approach. I'm copying it from another thread:

"Sanctioned clubs are subject to a monitoring period of a year or more. In most cases, they are subject to a 3-year monitoring period, in which UEFA wants to see that the club meets its financial obligations over time. What I wanted to study in this matter is what happens after the 3-year monitoring period, because that's how you can tell if the UEFA fair play regulations are effective. For example, if sanctions were imposed on a club in 2014, and the club is subject to a 3-year monitoring period, then I would like to see what happens in the three years following the monitoring period (2018-2021). If, for example, the club's expenses on player transfers have increased, this does not necessarily mean that the regulation is ineffective, but it is possible that they have increased but not to the level that existed before sanctions were imposed on the club (but somewhere in the middle). That's why I need to compare a few years after the monitoring period in relation to the period before the sanctions on the club. Do you have any idea how can I estimate it?"

Basically, what I'm asking is if and how I can compare periods 4,5,6 to periods -1,-2,-3 in the staggered DiD.

[Luca Toni]

Still looking for help regarding to csdid approach in respect to my research question (look above).

I would highly appreciate any help!

[Luca Toni]

Hi
This is not due to GVAR but your ivar and tvar.
Try the following, what happens if you do
xtset team year

If it gives you an error, then ID why, fix it and then come back to CSDID

Hey,
so I run the command "estat all" and unfortunately I got a statistically significant pvalue. That means that pre-trends are not parallel, right? what can I do in this case? the ATT is significant though. I worked on this project a lot, just to find out that my parallel trends assumption doesn't hold.
My dependent variable was volatile, so I knew that the parallel assumption might not hold. I did RDD with period as a running variable and it was significant around the cutoff (period 0). I wanted to do staggered DiD as well to check how periods 4,5,6 behave comparing to periods -1,-2,-3, which is something that I can't do with RDD since it's not around the period 0 cutoff but few periods later.