Identification with Models and Exogenous Data Variation

Forthcoming, Foundations and Trends in Accounting

Ross School of Business Paper No. 1323

12 Pages Posted: 2 Jul 2016 Last revised: 11 Oct 2016

R. Jay Kahn

University of Michigan, Stephen M. Ross School of Business, Students

Toni M. Whited

University of Michigan, Stephen M. Ross School of Business; National Bureau of Economic Research

Date Written: July 1, 2016

Abstract

We distinguish between identification and establishing causality. Identification means forming a unique mapping from features of data to quantities that are of interest to economists. Establishing causality is synonymous with finding sources of exogenous variation. These two issues are often confused. However, exogenous variation is only sometimes necessary and never sufficient to identify economically interesting parameters. Instead, even for causal questions identification must rest on an underlying economic model. We illustrate these points by examining identification in two recent papers: one causal study relying on an entirely verbal model and one non-causal study relying on a formal mathematical model.

Keywords: Identification, Causality, Natural Experiments, Structural Estimation

JEL Classification: G30,C10,M40

Suggested Citation

Kahn, R. Jay and Whited, Toni M., Identification with Models and Exogenous Data Variation (July 1, 2016). Forthcoming, Foundations and Trends in Accounting; Ross School of Business Paper No. 1323. Available at SSRN: https://ssrn.com/abstract=2803263 or http://dx.doi.org/10.2139/ssrn.2803263

R. Jay Kahn

University of Michigan, Stephen M. Ross School of Business, Students ( email )

Ann Arbor, MI
United States

Toni M. Whited (Contact Author)

University of Michigan, Stephen M. Ross School of Business ( email )

701 Tappan Street
Ann Arbor, MI MI 48109
United States

National Bureau of Economic Research ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Paper statistics

Downloads
482
Rank
47,019
Abstract Views
1,228