“…In addition to the Ashenfelter and Kreuger (1994) twins data, replicates have been given by Barron, Berger, and Black (1997a), Card (1996), Freeman (1984, Kaestner, Joyce, and Wehbeh (1996), Loewenstein and Spletzer (1998), Mellow and Sider (1983), Romeo (1997), and Romeo and Sun (1996). Alternatively, other studies have examined the accuracy of data by comparing questionnaire responses to administrative data (Bollinger 1998;Bollinger and David 1997;Bound, Brown, Duncan, andRodgers 1990,1994;Bound and Krueger 1991;Duncan and Hill 1985;Marquis, Marquis, and Polich 1986;Rodgers, Brown, and Duncan 1993). Taken together, these studies offer little support for the classic EVM; measurement error often exhibits a covariance with the true value.…”