Theory, Research Design Assumptions, and Causal Inferences

23 Pages Posted: 2 Jul 2019

See all articles by Chris Armstrong

Chris Armstrong

University of Pennsylvania - Accounting Department

John D. Kepler

Stanford Graduate School of Business

Date Written: August 9, 2018

Abstract

Ferri, Zheng, and Zou test Fischer and Verrecchia’s (2000) prediction that a reduction in investors’ uncertainty about managers’ financial reporting objectives leads to an increase in the valuation-relevance of earnings reports. They use mandatory CD&A disclosures as an arguably exogenous “shock” that provided investors with more precise information about managers’ contractual incentives and find that these enhanced disclosures increased the relation between firms’ unexpected earnings and stock returns. Using Ferri et al. as a backdrop, we discuss the implicit assumptions invoked in natural experimental research designs and the fundamental role of theory in drawing causal inferences from empirical evidence.

Keywords: Causal inference; quasi-natural experiments; disclosure theory

JEL Classification: C10; C50; M40; M41

Suggested Citation

Armstrong, Chris S. and Kepler, John, Theory, Research Design Assumptions, and Causal Inferences (August 9, 2018). Journal of Accounting & Economics (JAE), Vol. 66, No. 2-3, 2018. Available at SSRN: https://ssrn.com/abstract=3411226

Chris S. Armstrong (Contact Author)

University of Pennsylvania - Accounting Department ( email )

3641 Locust Walk
Philadelphia, PA 19104-6365
United States

John Kepler

Stanford Graduate School of Business ( email )

655 Knight Way
Stanford, CA 94305-5015
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
111
Abstract Views
430
rank
252,487
PlumX Metrics