GustavFlorinAagren
GustavFlorinAagren
When you say working example, do you mean data and code for the project?
I see. Well then interestingly this call (with the fixest example data called base_did) doesn't render the same problem: data(base_did) est_did
Realizing that the example I created had an x1-variable first on the RHS before the i(), I tried the same using my data on a model with an additional variable...
Using the base_did data and the call I used when I got the NAs (in the first post) does not produce the same error. I guess it must have to...
Here is part of the data and part of the code I use. This will produce the same error when trying to estimate the standard errors with CR2 and Satterthwaite...
Hi @jepusto ! Can I ask if you have taken a look at the data and the output I posted?
Thanks for your fast reply. Fantastic that you want to look into it. Thanks!
Hi! I know of the solution to use relevel. But it ends up the same way anyway: Call: lm_robust(formula = logwealth ~ treat:relevel(as.factor(Year), ref = "2006"), data = AJZ, clusters...
Hi @s3alfisc! Thanks for your reply. As you mention, the clubSandwich package does not support fixest with is unfortunate for me. I think I'll try the sandwich package solution. But...