Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We illustrate problems of measuring discrimination using elections to AEA offices. With a new econometric technique, we find female candidates have a much better than random chance of victory. This advantage is either reverse discrimination or reflects beliefs that women are more productive. The former interpretation could be explained by an unchanging median voter whose preferences were not satisfied by suppliers of candidates; but there was a structural change in voting behavior in the mid-1970s. The results suggest it is generally impossible to claim differences in rewards, for different groups measure the extent of discrimination or even its direction. (JEL A11, D72, J16)