The Reverse Regression Problem: Statistical Paradox or Artefact of Misspecification?

The usual approach to wage discrimination asks whether certain individuals receive lower wages for the same level of productivity characteristics. The reverse approach asks whether these individuals are more productive given the same wages. When these hypotheses are tested, incompatible conclusions seem to result. To circumvent specification problems, nonparametric techniques were used to estimate Canadian male-female wage/experience profiles. The findings indicate that, when the correct functional form is specified and the effects of childrearing activities are controlled for, there exists a wage/experience gap favoring men regardless of the approach, suggesting that the paradox may be simply an artifact of misspecification.