Dear statalisters,
I wonder why areg and xtreg do not give the same standard errors with the robust option.
More specifically, I want to know which method “preferred” in terms of standard errors, the XTreg or the areg, given a big dataset with many groups and uneven number of observations in each group.
I saw related discussions, but couldn’t find one to answer my specific question.
Thanks,
Omer Gold
Related (and helpful) discussions:
https://www.stata.com/statalist/arch.../msg00266.html
https://www.stata.com/support/faqs/s...rsus-xtreg-fe/
Example:
sysuse auto, clear
gen time = _n
xtset rep78 time
areg price mpg gear_ratio foreign , absorb(rep78) robust
xtreg price mpg gear_ratio foreign, fe robust
I wonder why areg and xtreg do not give the same standard errors with the robust option.
More specifically, I want to know which method “preferred” in terms of standard errors, the XTreg or the areg, given a big dataset with many groups and uneven number of observations in each group.
I saw related discussions, but couldn’t find one to answer my specific question.
Thanks,
Omer Gold
Related (and helpful) discussions:
https://www.stata.com/statalist/arch.../msg00266.html
https://www.stata.com/support/faqs/s...rsus-xtreg-fe/
Example:
sysuse auto, clear
gen time = _n
xtset rep78 time
areg price mpg gear_ratio foreign , absorb(rep78) robust
xtreg price mpg gear_ratio foreign, fe robust
