sergiocorreia / reghdfe

Linear, IV and GMM Regressions With Any Number of Fixed Effects
http://scorreia.com/software/reghdfe/
MIT License
219 stars 57 forks source link

i.id and absorb(id) yield different coefficient values #228

Open sungyupjung opened 3 years ago

sungyupjung commented 3 years ago

I am running a panel regression with year and region fixed effects. I am getting different coefficient values for

(1) reghdfe y x i.year, absorb(region) (2) reghdfe y x, absorb(year region)

where x consists of indicator variables that pertain to treatment periods (periods before and after treatment)

For (1) I have one year dummy omitted due to colinearity wheres for (2) I have one of the x's being omitted due to colinearity. So the coefficient values for x in (1) and (2) are quite different. Does anyone have any idea why this would be the case?