Hi everyone,

I am trying to estimate the effect of the mean establishment wage on a worker's future wage separately for males and females. What I did for now was including a c.meanwage#female interaction that gave me two separate estimates of the effect of meanwage (one for males and one for females), while additionally controlling for gender:

Code:
reghdfe workerwage_t1 c.meanwage#female workerwage, absorb(age tenure female occupation education year) vce(cluster establishment)
However, I was wondering whether it would be better to include meanwage separately to my estimation, so that c.meanwage#female would give me how the effect of meanwage is different for females (if males are the baseline category).


Code:
reghdfe workerwage_t1 c.meanwage#female workerwage meanwage, absorb(age tenure female occupation education year) vce(cluster establishment)
hat is, the effect for males would correspond to the coefficient estimate of meanwage and the effect for females to the coefficient estimates meanwage + c.meanwage#female. However, I am unsure how to deal with standard errors under this method.

Any help would be greatly appreciated!