xi: areg and areg

[Jaiwon Lee]

Hi!

I am running regressions involving patient fixed effects and year fixed effects.
I am not quite sure how do two commands below differ.

1) xi: areg y x i.year, absorb(patient id)
2) areg y x i.year, absorb(patient id)


I can see the coefficients are different but I don't get why do they differ....

Thanks in advance!

[Clyde Schechter]

Actually, they should not be different. The results should be the same. Please post back showing the exact complete commands you gave and the output Stata gave you so somebody can try to figure out what is going on.