Testing the effects of an unobservable factor: Do marriage prospects affect college-major choice?


Econometrics Seminar

United States

More on Tong Li

Signup Sheet

AbstractMotivated by studying the effects of marriage prospects on students’ college-major choices, this paper develops a new econometric test for analyzing the effects of an unobservable factor in a setting when this factor potentially affects both agents’ polychotomous choices and a binary dependent outcome variable. Our test takes its basis from a flexible copula-based estimation procedure and utilizes an ordered nature of latent utilities of the polychotomous choice model. Using the proposed method, we show that marriage prospects significantly affect students’ college-major choices of college graduates of National Longitudinal Study of Youth (97) Survey participants. Furthermore, we verify the robustness of our findings with alternative tests using stated marriage expectation measures in our data and show the validity of our test procedure in real-life applications.

Tong Li

Tong Li

Vanderbilt University