Hello Everybody,
I am trying to run RDD and I am wondering if what I would like to do is possible:
- I have a panel data of 5 years and I am looking at income at 60 years old.
- In the panel, some people turn 60 in wave 1, some in wave 3, some wave 5, etc.
- I would only like to look at the income at 60 in each wave because at the other ages after 60 years it doesn't matter or the individual does not get treated.
- What I thought will address this problem is to drop income observations after 60 years (the command: replace income=. if age>60). However, when running rdrobust, the model does not want to run (rdrobust income age, c(60). The error is: c() should be set within the range of age.
Is there any other way to do this? Or I need to keep the data in its original form?
Thanking you in advance.
