Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
The standard approach to mea suring earnings differentials is extended to include a female participation deci sion, and the effectsof sample selection are analyzed. A substantial proportion of the earnings differential between men and women in the U.K. graduate labor m arket can be attributed to residual factors rather than attributes and character istics. Womens' earnings could be as much as18 percent higher if these factors were removed. A statistically significant sample selection effect is present, bu t its quantitativeimpact on the measures of the residual differential is variab le. Thedata are sufficiently comprehensive to justify wider academic interest. Copyright 1986 by Royal Economic Society.