Is vce(r) option in XTIVREG HAC robust?

[Harry Oleary]

I have been trying to figure out a way to report HAC standard errors for a fixed effects instrumental variables regression. According to the post https://www.statalist.org/forums/for...nel-data-model, using the vce(r) option in xtreg reports standard errors that are robust to heteroskedasticity and panel autocorrelation. I was wondering if this is also the case for XTIVREG? If not, is there another way to provide HAC standard errors from within the same regression command?

[Andrew Musau]

That is true for any xt-prefixed estimation command in Stata. You can check the PDF manual entry for details.

h xtivreg