Hi all,
I'd appreciate any help in this matter.
I'd appreciate any help in this matter.
Code:
. . tab year
year | Freq. Percent Cum.
------------+-----------------------------------
2010 | 2,447 9.98 9.98
2011 | 2,447 9.98 19.96
2012 | 2,453 10.00 29.97
2013 | 2,453 10.00 39.97
2014 | 2,453 10.00 49.98
2015 | 2,453 10.00 59.98
2016 | 2,453 10.00 69.99
2017 | 2,453 10.00 79.99
2018 | 2,453 10.00 90.00
2019 | 2,453 10.00 100.00
------------+-----------------------------------
Total | 24,518 100.00
. tab cohort paypar
| paypar
cohort | 0 1 | Total
---------------+----------------------+----------
Never treated | 15,130 0 | 15,130
2011 | 0 1,330 | 1,330
2013 | 0 1,300 | 1,300
2014 | 0 1,150 | 1,150
2015 | 0 1,120 | 1,120
2016 | 0 2,908 | 2,908
2017 | 0 1,530 | 1,530
2018 | 0 50 | 50
---------------+----------------------+----------
Total | 15,130 9,388 | 24,518
Code:
. hdidregress aipw (active hospitals population disabled
> to beneficiaries totalcosts visitsper1kmedicarebenef) (paypar zscore1), group
> (statefips) time(year)
note: variable _did_cohort, containing cohort indicators formed by treatment variable paypar and group
variable statefips, was added to the dataset.
units in time period 2011 cannot be treated
The first time period in the estimation sample is 2011. This implies units are either always treated
or are switching between treatment and control, which violates the model's assumptions. You may look
at variable _did_cohort to diagnose this behavior.
r(498);
end of do-file
r(498);
Comment