this paper was circulated as Princeton liversity, Industrial Rela- tions Section Working Paper No. 108 and was written ile the first author was visiting Princeton at the Industrial Relations Sec6ion. The current version was written while the second author was visiting the Centre for Labour Economics (C.L.E.) at the London School of Economics. Helpful comments from Daniel Hamermesh Gregg Lewis, Sherwin Rosen and especially Orley Ashenfelter are gratefully acknowledged. Financial support was provided by the S.S.R.C. and the C.L.E. ESTIMATING THE UNION/NON-UNION WAGE DIFFERENTIAL: A STATISTICAL ISSUE Charles Mulvey and John M. Abowd Prior to the availability of micro-data sets for the U.S. which indicated the union or non-union status of individuals, almost all estimates of the conditional average union/non'-union wage differential, given union membership, were made using mean average wages from a sample of industries or occupations
No takes yet. Share an insight, caveat, or question.
Mulvey et al. (1980) studied this question.