<p>We design an experiment to infer true overconfidence in relative ability through actions, as opposed to reported beliefs. Subjects choose how to invest earnings from a skill task where the returns depend either solely upon risk, or both risk and relative placement, enabling joint estimation of individual risk preferences and implied subjective beliefs of placing in the top half. We find evidence of aggregate overconfidence only in a treatment that receives minimal feedback on performance in a trial round. In treatments that receive more detailed feedback aggregate overconfidence is not observed, however identifiable segments of over- and underconfident individuals persist.</p>