Publication Type

Journal Article

Version

submittedVersion

Publication Date

4-2023

Abstract

We study the informational content of factor structures in discrete triangular systems. Factor structures have been employed in a variety of settings in cross sectional and panel data models, and in this paper we attempt to formally quantify their informational content in a bivariate system often employed in the treatment effects literature. Our main findings are that under the factor structures often imposed in the literature, point identification of parameters of interest, such as both the treatment effect and the factor load, is attainable under weaker assumptions than usually required in these systems. For example, we show is that an exclusion restriction, requiring an explanatory variable in the outcome equation not present in the treatment equation is no longer necessary for identification. Furthermore, we show support conditions of included instruments in the outcome equation can be substantially weakened, resulting in settings where the identification results become regular. Under such settings we propose a estimators for the treatment effect parameter, the factor load, and the average structural function that are root-n consistent and asymptotically normal. The estimators’ finite sample properties are demonstrated through a simulation study and in an empirical application, where we implement our method to the estimation of the civic returns to college, revisiting the work by Dee (2004).

Keywords

Factor Structures, Discrete Choice, Treatment Effects

Discipline

Information Security | Management Information Systems

Research Areas

Econometrics

Publication

Advances in Econometrics

Volume

45B

First Page

385

Last Page

410

ISSN

0304-4076

Additional URL

http://www.econ.msu.edu/seminars/docs/ShakeebKhan paper.pdf

Download

Share

COinS