Am 06.02.2024 um 17:15 schrieb Brian Revell:


Wrt the LSDV fixed effects panel model test result for intercepts. It is helpful up to a point. However, if equal intercepts are rejected, does oneĀ  resort to OLS pooled data with DVs to see which differ as this is normally a matter of interest. I can see no way from the LSDV option itself to uncover the panel unit dummies relative to the estimated value of the constant.

OK, this is another question. You can save the unit-specific intercepts in the fixed-effects model window through Save / Group-specific intercepts.

Typically, though, you would simply run panel FE. It is not normally needed or wise to try to retain only a subset of the specific intercepts. (Note that the standard way of estimating does not involve literal LSDV, but uses the within transformation.)

cheers

sven