Data Science Seminar
Hosted by the Department of Mathematics and Statistics

Abstract


Exogenous participation is a common assumption used in empirical auctions to nonparametrically identify the model primitives. Despite the identifying power it provides, the assumption is not brought by any economic insight and thus is nonstrategic in nature. This paper proposes a test for exogenous participation in an ascending auction model with symmetric independent private values and additively separable unobserved heterogeneity. The testable implications are drawn from a new identification result which shows that exogenous participation has sufficient identifying power even in the absence of observations on participation. The proposed specification test based on moment inequalities makes inference via the discrepancy between the induced and observed participation distribution and controls size over a class of data generating processes.

Biography of the speaker: Dr. JoonHwan Cho is an assistant professor in the Economics Department at Binghamton University. He received his Ph.D. in Economics from the University of Toronto. His research interests lie in econometrics and empirical industrial organization.