Hi, pardon my ignorance in statistics. I am really confused when journal papers say that they run their regression using robust standard errors clustered at firm level. I tried two ways to do that and they gave me different results. Which should I be using?
1. reg, dep indep i.year, robust cluster(ID)
2. reg, dep indep i.year, vce (cluster ID)
1. reg, dep indep i.year, robust cluster(ID)
2. reg, dep indep i.year, vce (cluster ID)