Partial identification in non-separable triangular models

Details

Supervisors

Van Bellegem, Sébastien

Faculty

Faculté des sciences économiques, sociales, politiques et de communication

Degree label

Master [120] en sciences économiques, orientation économétrie

Abstract

We define an identification region and an estimator for the regression function $g(X, \varepsilon)$ of non-separable triangular models in the case where data is supposed to follow a general missing data pattern. We use fundamental concepts of partial identification, the generation of the unobservable random term $\varepsilon$ from within the model and assumptions on the instrumental variable to do so. General results are given and an empirical example is presented.