War Discourse and Disaster Premia: 160 Years of Evidence from Stock and Bond Markets

103 Pages Posted: 9 May 2023 Last revised: 7 Aug 2023

See all articles by David A. Hirshleifer

David A. Hirshleifer

Marshall School of Business, USC; National Bureau of Economic Research (NBER)

Dat Mai

University of Missouri at Columbia

Kuntara Pukthuanthong

University of Missouri, Columbia

Date Written: May 18, 2023

Abstract

Using a semi-supervised topic model on 7,000,000 New York Times articles spanning 160 years, we test whether topics of media discourse predict future stock and bond market returns to test rational and behavioral hypotheses about market valuation of disaster risk. Focusing on media discourse addresses the challenge of sample size even when major disasters are rare. Our methodology avoids look-ahead bias and addresses semantic shifts. War discourse positively predicts market returns, with an out-of-sample R2 of 1.35%, and negatively predicts returns on short-term government and investment-grade corporate bonds. The predictive power of war discourse increases in more recent time periods.

Keywords: War, disaster risk, machine learning, topic modelling, predictability, out-of-sample test

JEL Classification: G00, G02, G1

Suggested Citation

Hirshleifer, David A. and Mai, Dat and Pukthuanthong, Kuntara, War Discourse and Disaster Premia: 160 Years of Evidence from Stock and Bond Markets (May 18, 2023). Available at SSRN: https://ssrn.com/abstract=4430327 or http://dx.doi.org/10.2139/ssrn.4430327

David A. Hirshleifer

Marshall School of Business, USC ( email )

Marshall School of Business
Los Angeles, CA 90089
United States

HOME PAGE: http://https://sites.uci.edu/dhirshle/

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Dat Mai

University of Missouri at Columbia ( email )

Columbia, MO 65201
United States

HOME PAGE: http://www.maiydat.com/

Kuntara Pukthuanthong (Contact Author)

University of Missouri, Columbia ( email )

Robert J. Trulaske, Sr. College of Business
403 Cornell Hall
Columbia, MO 65211
United States
6198076124 (Phone)

HOME PAGE: https://www.kuntara.net/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
205
Abstract Views
823
Rank
260,779
PlumX Metrics