Dear All, Consider the following standard estimation of FE (fixed-effect) and RE (random-effect) model in (1) and (2):
Code:
webuse grunfeld, clear
xtset company year
// (1) fixed-effect
xtreg invest mvalue kstock i.year, fe robust
outreg2 using fere, word dec(4) ctitle(fe) replace
// (2) random-effect
xtreg invest mvalue kstock i.year, robust
outreg2 using fere, word dec(4) ctitle(re) append
// (3) fixed-effect + random-effect?
xtreg invest mvalue kstock i.company i.year, robust
outreg2 using fere, word dec(4) ctitle(fe+re) append
However, I have seen several papers using (3) to estimate the FE model (compared to (1), same estimates but different standard errors). What would be the problem by doing so? Thanks.