Dear all,
after using the Blinder-Oaxaca decompostion to decompose the African American/ White wage differential into an explained and an unexplained part seperatly for metropolitan (pwtype==1) and non-metropolitan (pwtype==0) areas I want to analyze if the unexplained wage differential is significantly different between metropolitan and non-metropolitan areas. The short form of my Oaxaca decompositions are:

oaxaca lnincwage sex educ educ2 lambda2 if pwtype==0, by(black) reference(betanonmetro) adjust(lambda2) noisily
estimate store ox1

oaxaca lnincwage sex educ educ2 lambda2 if pwtype==1, by(black) reference(betametro) adjust(lambda2) noisily
estimate store ox2

I wanted to do an unequal ttest now. I found codes which used suest but when I tried: suest ox1 ox1
I got the error message: ox1 was estimated with a nonstandard vce (robust)
Including vce(analytic) in the oaxaca was not possible.
I would appreciate it a lot if you could help me. Thank you very much!