[Tobias Berger]

Thanks a lot Carlo.

When testing with the Mundlak approach as you suggested, should I also test year effects with testparm when using clustered robust standard errors?
Clustered robust standard errors control also for heteroskedasticity right?

My regression code would look like:

xtreg lROA i.year lICrat lFL at lEff g_sales_w g_at_w lProfMar lICturn, fe cluster(gsubind2)

testparm i.year

[Carlo Lazzaro]

Tobias:
1) you can go -testparm- regardless of the tyoe of standard error;
2) Yes. Clustered robust standard errors control for both serial correlation of the epsilon and heteroskedasticity.