It has been suggested by Angrist and Pischke that Robust (i.e. robust to heteroskedasticity or unequal variances) Standard Errors are reported as a matter of course rather than testing for it. Two questions:

(1) What is impact on the standard errors of doing so when there is homoskedasticity? (2) Does anybody actually do this in their work?

It has been suggested by Angrist and Pischke that Robust (i.e. robust to heteroskedasticity or unequal variances) Standard Errors are reported as a matter of course rather than testing for it. Two questions:

1. What is impact on the standard errors of doing so when there is homoskedasticity?
2. Does anybody actually do this in their work?