Determining the causality between U.S. presidential prediction markets and global financial markets

Abstract

Prediction markets trade securities with final prices contingent on the outcome of future events, for example, who will win the next political election. We show how the outcome of a United States presidential election, information captured by prediction markets, impacts global financial markets. We investigate the existence of a causal relationship between various prediction markets and global financial markets time series for over 27 different countries and regions using Dow Jones Global Indexes. We construct vector auto‐regressive models and use the Toda–Yamamoto causality test to deal with non‐stationary time series. Preliminary results indicate that prediction markets may be used to predict some global financial markets.