Running multiple subgroups

[Ivan Ivanov]

Hi,

My code is the following:

xtset id year

xtreg y x1 x2 x3 i.year, fe vce (cluster id)

I am trying to estimate whats the effect of x1 on y. However my variable x1=xa+xb+xc. Furthermore, I have xx=xa, whereas xz=xb+Xxc.

Now my question is, if I want to check whether group xz has bigger effect on y than xx does, do I run two separate regressions:

xtreg y xx x2 x3 i.year, fe vce(cluster id)

xtreg y xz x2 x3 i.year, fe vce(cluster id),

and then look at their coefficients

or one regression:

xtreg y xx xz x2 x3 i.year, fe vce(cluster id) and then look at their coefficients?

Furthermore, if I want to control for time fixed effects, I add i.year but if I want to control for id fixed effects, I don't have to because when using fe, STATA does it automatically?

Thank you very much.

[Carlo Lazzaro]

Ivan:
see -help suest-.