World War II veterans earn more than nonveterans in their cohort. We test whether the World War II veteran premium reflects nonrandom selection into the military of men with higher earnings potential. The estimation is based on the fact that from 1942 to 1947 priority for conscription was determined by date of birth. Information on individuals' dates of birth may therefore be used to construct instrumental variables for veteran status. Empirical results from the 1960, 1970, and l980 censuses, along with two other microdata sets support a conclusion that World War II veterans earn no more than comparable nonveterans and may well earn less. Copyright 1994 by University of Chicago Press.