In addition to discrimination, market power, and human capital, gender differences in risk preferences might also contribute to observed gender wage gaps. We conduct laboratory experiments in which subjects choose between a risky (in terms of exposure to unemployment) and a secure job after...

Probit and logit models typically require a normalization on the error variance for model identification. This paper shows that in the context of sample mean probability decompositions, error variance normalizations preclude estimation of the effects of group differences in the latent variable...