Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We advocate a different approach to measure the gender gap, summarizing each distribution by suitable evaluative functions and computing the difference between the evaluations. Unlike the conventional approach, ours does not assume rank invariance. We discuss the decision-theoretic framework behind different functions and introduce measures based on entropy functions. We further adopt quantile-copula approaches to account for selection into full-time employment and discuss how to take into account nonmarket values in measuring the gap. The evolution of the gender gap depends on the measure of it and whether nonmarket values are incorporated. We further assess and challenge a variety of assumptions, hypotheses, and findings in the literature.