Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This article provides an approach to test whether greater heterogeneity of contestants leads to lower effort exertion in elimination tournaments, as predicted by conventional tournament models. This prediction is difficult to test with real world data because the effort is difficult to measure. Based on a simple behavioural model, testable implications are derived and an identification strategy is suggested that allows to test for an incentive effect of heterogeneity even when the effort is unobservable. The application uses data from professional tennis tournaments and provides evidence that heterogeneity affects the incentives to exert effort.