Greetings!

Please, I'd like to know and make sure whether Driscoll-Kraay standard error model approach (xtscc) able to deal with non-stationary panel data set (for instance, I(1) or mixed I(0) I(1))? Or stationarity I(0) of the panel is a requirement?

In my case, DV(1); key IV(0) and other control variables IV(1).

Would be glad to hear from you and learn from your expertise.

Thanks beforehand.

References to the xtscc approach: http://fmwww.bc.edu/repec/bocode/x/xtscc.ado
Also see: The Stata Journal, "Robust Standard Errors for Panel Regressions with Cross-Sectional Dependence" by Daniel Hoechle

Best regards.