I am using the rdrobust command to estimate a (continuity based) regression discontinuity regression. I need to account for individual fixed effects. To do so, I use indicator variables. When I run the regression, after some time, I get an error saying that there is an invertibility issue and it stops running. My panel data includes about 10,000 individuals with many monthly observations. But I am sure the number of observations is not the problem because I run the regressions on sub-groups and in some large groups the regressions get estimated with no problems, while in few smaller ones they do not. So I am not sure what the problem is. What can I do?
-
Login or Register
- Log in with
