Recovering Election Winner Probabilities from Stock Prices

Abstract

After the 2020 U.S. presidential election, counting votes and calling states took more time than usual, particularly in battleground states. In the days following the election, winning probabilities changed frequently as new results were tabulated. Based on the sensitivity of stocks to changes in winning probabilities observed before the election, we show how the stock market’s assessment of the unobserved postelection winning probabilities can be backed out from stock prices. Our approach is based solely on publicly available data.

Type
Publication
Working Paper
Implied Republican winning probabilities on Nov. ,4 2020, calculated from intraday prices. Vertical lines indicate the time (ET) when the respective state was called by Associated Press. Solid/dashed/dotted lines are for decile/quintile/tercile portfolios. Results from value-weighted (equally-weighted) portfolios are shown in red (blue).
Implied Republican winning probabilities around Election Day (Nov. 3, 2020). Left: Results from the portfolio approach, using daily closing prices. Solid (dashed) lines indicate probabilities calculated when including stocks whose sensitivities $\theta_i$ are significant at the 10% (5%) level. Results from value-weighted/equally-weighted/median portfolios are shown in red/blue/turquoise. Right: Results from the regression approach, using daily closing prices. Solid/dashed/dotted lines are for decile/quintile/tercile portfolios. Results from value-weighted (equally-weighted) portfolios are shown in red (blue).

Related